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

    Neuronpedia

    INDEX
    Explanations

    pairs of opposing concepts or qualities

    oai_token-act-pair · gpt-3.5-turbo

    connective words indicating relationships, such as conjunctions and coordinating phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essage
    -0.68
    iew
    -0.68
    Picture
    -0.68
    during
    -0.67
    stocks
    -0.67
    ynthesis
    -0.67
    :[
    -0.66
    utic
    -0.65
    swick
    -0.65
    bos
    -0.64
    POSITIVE LOGITS
    rogens
    0.84
    rogen
    0.82
     vice
    0.76
     lin
    0.75
     etc
    0.71
     decay
    0.71
     blah
    0.68
     amen
    0.67
     adj
    0.67
     assorted
    0.66
    Act Density 0.375%

    No Known Activations