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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iesel
    -0.17
    pitch
    -0.16
    urgeon
    -0.15
    /trunk
    -0.15
     Jag
    -0.15
    opsis
    -0.15
    Pitch
    -0.15
    ough
    -0.14
    Ñĩи
    -0.14
    bsub
    -0.14
    POSITIVE LOGITS
     Canter
    0.17
    ائج
    0.15
     Boss
    0.14
     mon
    0.14
    ãĥ«ãĥķ
    0.14
    ATYPE
    0.13
     Levin
    0.13
     pot
    0.13
     ticking
    0.13
    Fa
    0.13
    Act Density 0.000%

    No Known Activations