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

    Neuronpedia

    INDEX
    Explanations

    numeric expressions and statistical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Including
    -0.64
     Lasting
    -0.62
     Carlton
    -0.61
     individualism
    -0.61
     perpetuity
    -0.60
     ſtate
    -0.60
     myſelf
    -0.60
     spont
    -0.60
     Washburn
    -0.60
    AndEndTag
    -0.59
    POSITIVE LOGITS
     very
    0.67
     صوتيه
    0.65
    非常的
    0.60
    tvguidetime
    0.59
     jesteśmy
    0.59
     vært
    0.58
     része
    0.57
     الدولى
    0.57
    pendidikan
    0.56
     blitt
    0.56
    Act Density 0.525%

    No Known Activations