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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "ale."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ale."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nl
    -0.80
    rontal
    -0.75
    ingen
    -0.74
    soDeliveryDate
    -0.73
    pread
    -0.71
    olicy
    -0.71
    ulates
    -0.68
    nect
    -0.66
     Beir
    -0.65
    ulate
    -0.65
    POSITIVE LOGITS
    xit
    0.96
    ttes
    0.93
    cki
    0.91
    ppo
    0.82
    uca
    0.81
    ea
    0.80
    jandro
    0.79
    ague
    0.77
    lla
    0.76
    ei
    0.74
    Act Density 0.012%

    No Known Activations