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

    Neuronpedia

    INDEX
    Explanations

    phrases inviting communication or feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ur
    -0.14
    arians
    -0.14
    anio
    -0.14
    gne
    -0.14
    ansen
    -0.14
    duk
    -0.14
    rys
    -0.14
    па
    -0.14
    fts
    -0.13
    .DOM
    -0.13
    POSITIVE LOGITS
     anytime
    0.18
    858
    0.16
     ÐĿаÑģ
    0.15
    698
    0.15
    .sap
    0.15
    ysa
    0.15
     yourself
    0.15
    634
    0.15
    770
    0.14
    374
    0.14
    Act Density 0.013%

    No Known Activations