Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant developments or consequences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "a"/"an" indicating progress/change

    np_acts-logits-general · gemini-2.0-flash

    significant positive developments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.69
     ContentValues
    -0.61
    lwjgl
    -0.60
     titolata
    -0.59
     nakalista
    -0.58
    suje
    -0.57
     disambiguazione
    -0.57
    ReusableCell
    -0.55
     eventdata
    -0.54
    ForValue
    -0.54
    POSITIVE LOGITS
     milestone
    1.08
     step
    0.98
     breakthrough
    0.90
     landmark
    0.86
     signal
    0.84
    SequentialGroup
    0.83
     stepping
    0.81
    milestone
    0.79
     boost
    0.75
    step
    0.75
    Act Density 0.301%

    No Known Activations