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

    Neuronpedia

    INDEX
    Explanations

    exclamations expressing strong emotions or frustrations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.76
    083
    -0.76
    iku
    -0.72
    Vert
    -0.69
    cit
    -0.68
    Ĭ±
    -0.67
    Joy
    -0.64
    士
    -0.63
    EStreamFrame
    -0.62
    hig
    -0.59
    POSITIVE LOGITS
     happened
    0.79
     else
    0.72
    ?!
    0.72
    !?"
    0.68
    holes
    0.67
     dude
    0.66
    !?
    0.66
    else
    0.65
    dar
    0.64
     rubbish
    0.64
    Act Density 0.021%

    No Known Activations