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

    Neuronpedia

    INDEX
    Explanations

    information about specific events or incidents, prompting the reader to provide details or tips

    oai_token-act-pair · gpt-3.5-turbo

    requests for information or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reality
    -0.70
    çķ
    -0.70
    pex
    -0.70
    sbm
    -0.69
    erenn
    -0.68
    literally
    -0.68
    æѦ
    -0.66
    once
    -0.65
    bread
    -0.65
    equal
    -0.65
    POSITIVE LOGITS
     whereabouts
    0.91
     spotting
    0.86
     inquiries
    0.82
     suggestions
    0.81
     voic
    0.81
     comment
    0.78
     bookmark
    0.78
     corrections
    0.77
     thoughts
    0.77
     discrepancy
    0.77
    Act Density 0.226%

    No Known Activations