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

    Neuronpedia

    INDEX
    Explanations

    abbreviated names or titles consisting of initials and numbers

    oai_token-act-pair · gpt-3.5-turbo

    certain numerical values and their corresponding elements, likely relating to scores or ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Versions
    -0.79
    kefeller
    -0.77
    uther
    -0.71
    ourses
    -0.70
    annabin
    -0.67
    ighters
    -0.63
    ibrary
    -0.61
    restling
    -0.61
    anchester
    -0.61
    oder
    -0.61
    POSITIVE LOGITS
     Brett
    0.74
     Marie
    0.69
     ours
    0.68
     theirs
    0.67
     yours
    0.64
     TJ
    0.64
     CoC
    0.63
    âĢİ
    0.62
     hers
    0.62
    boss
    0.62
    Act Density 0.052%

    No Known Activations