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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate guidance or instruction

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

    what to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BorderSide
    -0.65
    httphttps
    -0.65
    Portály
    -0.60
     nakalista
    -0.56
    сылкі
    -0.56
    Cyfarwyddwr
    -0.55
     noDo
    -0.54
    sizeCache
    -0.53
    лтамалар
    -0.52
     disambiguazione
    -0.52
    POSITIVE LOGITS
     what
    0.55
    what
    0.51
    toMatch
    0.50
    何を
    0.49
     What
    0.48
    What
    0.47
     beſt
    0.46
     WHAT
    0.45
    WHAT
    0.45
     NORM
    0.44
    Act Density 0.005%

    No Known Activations