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

    Neuronpedia

    INDEX
    Explanations

    references to sourced information or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    self
    -0.17
    leen
    -0.15
    rone
    -0.15
     Live
    -0.14
     observ
    -0.14
    hip
    -0.14
    rego
    -0.14
    995
    -0.14
    iously
    -0.14
     testament
    -0.13
    POSITIVE LOGITS
    ÑĤеÑĢи
    0.16
    ERCHANT
    0.15
    artz
    0.15
    ertz
    0.15
    ongoose
    0.15
    riere
    0.14
    ERING
    0.14
    ahan
    0.14
    Jvm
    0.14
    acom
    0.14
    Act Density 0.004%

    No Known Activations