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

    Neuronpedia

    INDEX
    Explanations

    words related to physical actions and violence

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and their patterns in phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.76
    iciary
    -0.70
     XY
    -0.68
     Sloan
    -0.67
    xus
    -0.63
    ographed
    -0.62
     Scully
    -0.62
     Guatem
    -0.62
     CN
    -0.61
     Guerrero
    -0.61
    POSITIVE LOGITS
    thur
    0.68
    tons
    0.68
    edge
    0.67
    itsch
    0.67
    oddy
    0.67
    argon
    0.67
    chest
    0.67
     IPM
    0.67
    anim
    0.67
    watching
    0.66
    Act Density 0.452%

    No Known Activations