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

    Neuronpedia

    INDEX
    Explanations

    terms related to various specific topics such as sexuality, finance, health, technology, and social issues

    oai_token-act-pair · gpt-3.5-turbo

    topics related to health, safety, and physical well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udos
    -0.58
     Hawks
    -0.53
    igel
    -0.51
    iencies
    -0.49
     pestic
    -0.48
     nods
    -0.46
    vice
    -0.46
     guesses
    -0.45
    uable
    -0.44
     caveats
    -0.44
    POSITIVE LOGITS
    .''.
    0.79
    .
    0.76
    .[
    0.72
    .</
    0.71
     »
    0.69
    .''
    0.66
    âĢİ
    0.65
     compared
    0.63
    :[
    0.63
    hess
    0.62
    Act Density 1.125%

    No Known Activations