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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or intended use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acci
    -0.16
    idor
    -0.15
    ymes
    -0.14
    вок
    -0.13
    eling
    -0.13
    ắt
    -0.13
     arresting
    -0.13
    Issuer
    -0.13
     GOODMAN
    -0.13
     æĿ
    -0.13
    POSITIVE LOGITS
     use
    0.42
     consumption
    0.36
    use
    0.32
     distribution
    0.28
     sale
    0.28
    Use
    0.28
    _use
    0.27
     uso
    0.26
     reuse
    0.26
     Use
    0.26
    Act Density 0.204%

    No Known Activations