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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating control and the need for evidence or demonstration in arguments

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

    by itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.55
    PDOException
    -0.52
     Exactos
    -0.49
     StatelessWidget
    -0.48
     Mundi
    -0.47
    RRect
    -0.46
    matchCondition
    -0.46
    NewLabel
    -0.46
     disambiguazione
    -0.46
    HostException
    -0.45
    POSITIVE LOGITS
     alleine
    0.70
     alone
    0.66
     allein
    0.65
     Allein
    0.63
    alone
    0.57
     ALONE
    0.56
    Alone
    0.52
    だけでも
    0.49
     Alone
    0.49
    solo
    0.48
    Act Density 0.070%

    No Known Activations