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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate action or agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /from
    -0.16
    doch
    -0.15
    ủi
    -0.15
    _Handler
    -0.15
    оÑĩ
    -0.15
    /*č↵
    -0.15
    .exist
    -0.14
    ska
    -0.14
    _invoke
    -0.14
    paragus
    -0.14
    POSITIVE LOGITS
     roles
    0.33
     role
    0.31
    role
    0.26
     a
    0.25
    roles
    0.25
     Role
    0.25
    Role
    0.23
     starring
    0.23
     important
    0.23
     Roles
    0.23
    Act Density 0.034%

    No Known Activations