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

    Neuronpedia

    INDEX
    Explanations

    terms related to identification and differentiation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Handlung
    -0.53
    Bronnen
    -0.51
     currentValue
    -0.50
    licante
    -0.48
    culum
    -0.47
    Transkript
    -0.47
    BUFF
    -0.46
     codecs
    -0.46
    (:,:,
    -0.46
    pti
    -0.45
    POSITIVE LOGITS
     identification
    0.98
     distinguish
    0.94
     distinguishing
    0.94
     Identification
    0.91
    Identification
    0.88
     differentiate
    0.86
     distinguishes
    0.85
    identification
    0.84
    distingu
    0.84
     identify
    0.84
    Act Density 0.686%

    No Known Activations