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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time or condition, such as "when," "if," or "once."

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing self-awareness and personal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WER
    -0.72
    oner
    -0.70
    bourg
    -0.68
     Kem
    -0.66
     Ain
    -0.63
    vision
    -0.63
    dor
    -0.63
    far
    -0.63
     âĶľ
    -0.62
     Mong
    -0.61
    POSITIVE LOGITS
    idth
    0.74
     collide
    0.72
    mble
    0.72
    roup
    0.71
     confronted
    0.70
     Chimera
    0.67
    entimes
    0.65
     ceases
    0.65
     otherwise
    0.64
    erva
    0.61
    Act Density 0.337%

    No Known Activations