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

    Neuronpedia

    INDEX
    Explanations

    specific words related to measurement, classification, or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igt
    -0.17
    vang
    -0.17
    oose
    -0.16
    rees
    -0.15
    enville
    -0.14
    rg
    -0.14
     Research
    -0.14
    RefCount
    -0.14
     Rig
    -0.14
     regular
    -0.14
    POSITIVE LOGITS
    ÑĢÑĮ
    0.15
     Dont
    0.14
     Jinping
    0.14
     Libert
    0.14
    .Utc
    0.14
    urred
    0.14
    _reporting
    0.13
    νηÏĤ
    0.13
    Ãły
    0.13
    rch
    0.13
    Act Density 0.018%

    No Known Activations