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

    Neuronpedia

    INDEX
    Explanations

    specific organizations or entities which have made public statements

    oai_token-act-pair · gpt-3.5-turbo

    definite articles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £ı
    -0.69
    hd
    -0.68
    gat
    -0.68
    "}
    -0.67
     exceeds
    -0.66
    rha
    -0.66
    ftime
    -0.65
    chan
    -0.65
    hene
    -0.65
    pai
    -0.64
    POSITIVE LOGITS
     same
    1.15
     latest
    1.07
     brunt
    1.07
     latter
    1.05
     largest
    1.02
     idea
    1.00
     infamous
    1.00
     following
    0.98
     toughest
    0.97
     aforementioned
    0.96
    Act Density 0.439%

    No Known Activations