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

    Neuronpedia

    INDEX
    Explanations

    questions ending with a question mark

    oai_token-act-pair · gpt-3.5-turbo

    questions that express confusion or seek clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apixel
    -0.75
     charism
    -0.74
    avorite
    -0.73
    respective
    -0.73
    apter
    -0.72
    uckland
    -0.71
    rament
    -0.68
    etheless
    -0.66
    ĸļ士
    -0.66
    alist
    -0.66
    POSITIVE LOGITS
     Surely
    1.25
     Why
    1.25
     Anyway
    1.23
     Isn
    1.20
     Where
    1.20
     What
    1.13
     Didn
    1.13
    ?!
    1.13
     Answer
    1.13
     Wouldn
    1.12
    Act Density 0.115%

    No Known Activations