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

    Neuronpedia

    INDEX
    Explanations

    phrases that inquire about methods or procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _DP
    -0.16
     Brent
    -0.15
    IDL
    -0.15
     lam
    -0.15
    ocator
    -0.15
     Lam
    -0.14
    yne
    -0.14
    lington
    -0.14
    aven
    -0.14
    azu
    -0.14
    POSITIVE LOGITS
    kla
    0.16
    oldt
    0.16
    otto
    0.16
    ool
    0.15
    éĭ
    0.14
     Kil
    0.14
     kari
    0.14
     fort
    0.14
    ulk
    0.14
    enk
    0.14
    Act Density 0.013%

    No Known Activations