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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "acting" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.70
    sbm
    -0.69
    fer
    -0.65
    joy
    -0.64
    roe
    -0.64
    nic
    -0.63
    pex
    -0.62
    gart
    -0.62
    paralle
    -0.61
    grown
    -0.61
    POSITIVE LOGITS
    uary
    1.02
    uate
    0.84
    Director
    0.83
     prov
    0.81
     director
    0.77
     PRESIDENT
    0.74
    uated
    0.74
    OTUS
    0.69
     adm
    0.69
     cz
    0.69
    Act Density 0.009%

    No Known Activations