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

    Neuronpedia

    INDEX
    Explanations

    prominent figures in various fields

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     justifies
    -0.74
     exceeds
    -0.73
     threatens
    -0.70
    chery
    -0.70
     destroys
    -0.70
     excludes
    -0.69
    styles
    -0.69
     eliminates
    -0.66
     overwhel
    -0.66
     rushes
    -0.66
    POSITIVE LOGITS
     holiest
    0.84
     acronym
    0.80
     largest
    0.76
     oldest
    0.75
     proud
    0.73
    igmatic
    0.71
     Mub
    0.69
     bedrock
    0.69
    quartered
    0.68
     latest
    0.68
    Act Density 0.265%

    No Known Activations