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

    Neuronpedia

    INDEX
    Explanations

    uppercase words or proper names

    oai_token-act-pair · gpt-3.5-turbo

    uppercase letters and specific letter combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kush
    -0.61
    NEWS
    -0.55
    DX
    -0.55
    VL
    -0.54
    yip
    -0.52
    enegger
    -0.52
    +.
    -0.51
     liking
    -0.51
     FISA
    -0.51
    VII
    -0.50
    POSITIVE LOGITS
    acies
    0.67
    anism
    0.64
    acious
    0.63
    agons
    0.61
    atism
    0.60
    angles
    0.60
    itized
    0.58
    icial
    0.58
    istically
    0.58
    igroup
    0.58
    Act Density 0.214%

    No Known Activations