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

    Neuronpedia

    INDEX
    Explanations

    words related to physical attack or aggression

    oai_token-act-pair · gpt-3.5-turbo

    references to "mugging" or the word "mug" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISION
    -0.82
    cision
    -0.69
     Virgin
    -0.69
    ×Ļ×
    -0.66
    ipher
    -0.66
    IGH
    -0.65
    Domin
    -0.65
     Physicians
    -0.64
    SOURCE
    -0.63
     Empires
    -0.63
    POSITIVE LOGITS
    gers
    1.16
    shots
    1.08
    ging
    1.07
    ger
    1.04
    itude
    1.01
    shot
    1.00
    atu
    0.93
    ged
    0.93
    gery
    0.93
    ifully
    0.92
    Act Density 0.009%

    No Known Activations