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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to a specific geographic location

    oai_token-act-pair · gpt-3.5-turbo

    references to British entities or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -1.02
    ovie
    -0.84
    ologies
    -0.83
    pty
    -0.82
    apego
    -0.81
    tp
    -0.79
    urated
    -0.77
    ographed
    -0.75
     tomat
    -0.74
    inarily
    -0.73
    POSITIVE LOGITS
     Isles
    1.31
     Columbia
    1.27
     Columb
    1.22
     Airways
    1.19
     Union
    0.93
     Crown
    0.91
     Steel
    0.90
     Parliament
    0.90
     Broadcasting
    0.90
     Forces
    0.89
    Act Density 0.022%

    No Known Activations