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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude towards the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uthor
    -0.60
     displ
    -0.60
    chio
    -0.60
    ño
    -0.59
     helicop
    -0.56
    wealth
    -0.53
    ignty
    -0.53
    gart
    -0.51
    senal
    -0.50
     Paddock
    -0.49
    POSITIVE LOGITS
    LOCK
    0.69
    irming
    0.62
     externalToEVAOnly
    0.61
    ा
    0.61
    RAY
    0.60
     subscribing
    0.60
    âĿ
    0.59
    yg
    0.58
    zbek
    0.58
    quished
    0.56
    Act Density 0.014%

    No Known Activations