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

    Neuronpedia

    INDEX
    Explanations

    statistics related to numbers of people affected by events or incidents

    oai_token-act-pair · gpt-3.5-turbo

    instances of the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¯
    -0.74
    NVIDIA
    -0.73
    POST
    -0.72
    ENS
    -0.70
    edia
    -0.65
    £
    -0.65
    olate
    -0.65
    LI
    -0.63
    scribe
    -0.63
    ukong
    -0.62
    POSITIVE LOGITS
     assorted
    0.95
     counting
    0.92
     totaling
    0.92
     apiece
    0.83
     equivalents
    0.73
     participated
    0.73
     injure
    0.71
     thereby
    0.70
     total
    0.69
     subsequ
    0.69
    Act Density 0.210%

    No Known Activations