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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authority or responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OTHERWISE
    -0.20
     otherwise
    -0.16
    pbs
    -0.15
    bai
    -0.15
    otherwise
    -0.15
    ÄIJT
    -0.15
    .mj
    -0.15
     actionTypes
    -0.14
     innocence
    -0.14
    volution
    -0.14
    POSITIVE LOGITS
     Ad
    0.16
    nv
    0.15
    outil
    0.14
    TintColor
    0.14
     Id
    0.14
    алÑĮ
    0.14
    ÏĢοÏį
    0.14
    ollo
    0.14
    alsa
    0.14
    Match
    0.13
    Act Density 0.025%

    No Known Activations