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

    Neuronpedia

    INDEX
    Explanations

    details about product specifications and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     somehow
    -0.14
     можно
    -0.14
    ohn
    -0.14
    asma
    -0.14
     hast
    -0.14
    arde
    -0.14
    enta
    -0.14
    ought
    -0.14
    á»ī
    -0.14
    osas
    -0.13
    POSITIVE LOGITS
     may
    0.36
    may
    0.33
     occasionally
    0.28
     ÙħÙħÚ©ÙĨ
    0.23
    sometimes
    0.23
     sometimes
    0.22
     might
    0.21
    åı¯èĥ½
    0.21
     можеÑĤ
    0.21
     Occasionally
    0.21
    Act Density 0.227%

    No Known Activations