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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and tools used in physical labor or construction contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    words
    -0.78
    ournal
    -0.74
    grading
    -0.74
    uses
    -0.69
    ctica
    -0.68
    usable
    -0.66
    etermined
    -0.65
    omas
    -0.65
     runaway
    -0.65
    eways
    -0.64
    POSITIVE LOGITS
     Weaver
    0.95
    gren
    0.77
    sburg
    0.75
     Herz
    0.71
     Springs
    0.70
    quist
    0.70
    ¯
    0.68
    lings
    0.65
    sonian
    0.65
    bats
    0.65
    Act Density 0.005%

    No Known Activations