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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or behaviors of individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    presence of pronouns and auxiliary verbs indicating action or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NSA
    -0.60
    oiler
    -0.59
     disclaimer
    -0.58
    ENSE
    -0.57
    ertodd
    -0.56
    igsaw
    -0.56
    geries
    -0.55
    ente
    -0.55
     Dmit
    -0.55
     Vaj
    -0.54
    POSITIVE LOGITS
     destined
    0.80
     formerly
    0.72
    ago
    0.69
     frequ
    0.69
     already
    0.68
     previously
    0.68
    SI
    0.66
     "$:/
    0.66
     otherwise
    0.66
    ufact
    0.66
    Act Density 0.256%

    No Known Activations