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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing a continuous or enduring action or sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     currently
    -0.25
     soon
    -0.19
     Currently
    -0.18
    currently
    -0.17
    Currently
    -0.17
     presently
    -0.16
    athe
    -0.16
    lama
    -0.15
    itzer
    -0.15
    缮åīį
    -0.15
    POSITIVE LOGITS
    ä¸Ģ缴
    0.17
    Always
    0.16
     ALWAYS
    0.16
    以æĿ¥
    0.16
     siempre
    0.15
    rovers
    0.15
     вÑģегда
    0.15
    (always
    0.15
     Always
    0.15
     بÙĪدÙĩ
    0.15
    Act Density 0.096%

    No Known Activations