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

    Neuronpedia

    INDEX
    Explanations

    terms related to free offers or free services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phalt
    -0.16
    llum
    -0.16
    mos
    -0.16
    phan
    -0.15
    nya
    -0.15
    sm
    -0.15
    NotFoundException
    -0.15
    naments
    -0.15
    sets
    -0.15
    sto
    -0.15
    POSITIVE LOGITS
    bies
    0.43
    bie
    0.41
    zers
    0.31
    -standing
    0.30
    zing
    0.29
    bsd
    0.28
     lance
    0.28
    -floating
    0.27
    zes
    0.27
    zer
    0.27
    Act Density 0.071%

    No Known Activations