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

    Neuronpedia

    INDEX
    Explanations

    terms related to behavior or characteristics in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to behavioral concepts and organizational structures

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

    Fires on UK spelling words (eg: "ou" instead of "o" and "s" instead of z")

    Explanation Uploaded by User
    New Auto-Interp
    Negative Logits
     VIDEOS
    -0.77
     Gott
    -0.70
    Shot
    -0.67
    士
    -0.65
    ECK
    -0.65
    thal
    -0.65
    gress
    -0.64
     Tanz
    -0.64
    outh
    -0.63
     Dull
    -0.63
    POSITIVE LOGITS
     Whilst
    0.81
     analyse
    0.77
    alysed
    0.74
     Firstly
    0.74
    uminium
    0.72
    ablishment
    0.72
    piece
    0.70
    colour
    0.69
    elaide
    0.69
     envis
    0.69
    Act Density 0.182%

    No Known Activations