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

    Neuronpedia

    INDEX
    Explanations

    political and professional titles or occupations

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles of individuals, particularly those who are former or in notable positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.67
    perate
    -0.67
    erity
    -0.66
    igs
    -0.63
    orsi
    -0.63
    izzle
    -0.61
    aber
    -0.60
    inters
    -0.60
    gall
    -0.59
    MpServer
    -0.58
    POSITIVE LOGITS
     extraord
    0.75
     laureate
    0.74
     Jerome
    0.74
     Jeffrey
    0.73
     Shy
    0.72
    Joined
    0.71
     Shaun
    0.70
     Mick
    0.70
     Sonia
    0.69
    abilia
    0.67
    Act Density 0.432%

    No Known Activations