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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and named entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ten
    -0.83
     Truman
    -0.82
     Morton
    -0.78
     Monarch
    -0.78
    142
    -0.77
     KR
    -0.74
     Sonny
    -0.73
     WP
    -0.72
    Ross
    -0.72
    Ten
    -0.71
    POSITIVE LOGITS
    ig
    1.85
    IG
    1.69
    igs
    1.67
    igg
    1.31
     Zig
    1.25
     IG
    1.23
     Mig
    1.22
    rig
    1.21
    igraph
    1.20
    igi
    1.19
    Act Density 0.369%

    No Known Activations