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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating interest or focus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibli
    -0.16
    ento
    -0.15
    اÙĬ
    -0.15
    ummer
    -0.15
     Tie
    -0.14
    å¯Ħ
    -0.14
     è¦
    -0.14
    axy
    -0.14
    aign
    -0.14
    cott
    -0.13
    POSITIVE LOGITS
    ongyang
    0.16
    lator
    0.15
    lfw
    0.14
     azimuth
    0.14
    lett
    0.14
     Gap
    0.14
    :animated
    0.14
    oleÄį
    0.14
     Logical
    0.14
     eiusmod
    0.14
    Act Density 0.019%

    No Known Activations