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

    Neuronpedia

    INDEX
    Explanations

    the start of a document or a key section within a document

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

    Tokens before a name or abbreviation

    np_acts-logits-general · gemini-2.0-flash

    words ending in 'inger' or related to dependence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.65
     Simply
    -0.65
     something
    -0.63
     Monfieur
    -0.63
     Cæsar
    -0.61
     themſelves
    -0.61
     thoſe
    -0.59
     ſtate
    -0.59
     simply
    -0.59
     Anw
    -0.58
    POSITIVE LOGITS
     belonged
    0.59
     ***!
    0.58
     onAnimation
    0.57
     gynhyrchwyd
    0.55
     honoured
    0.54
     invokingState
    0.52
    URLException
    0.51
     belong
    0.51
    findpost
    0.50
    RectangleBorder
    0.49
    Act Density 0.194%

    No Known Activations