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

    Neuronpedia

    INDEX
    Explanations

    terms associated with magnitude or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lessly
    -0.17
    uren
    -0.16
    criptor
    -0.15
    agine
    -0.15
    ively
    -0.15
    bsolute
    -0.15
    semble
    -0.14
    urally
    -0.14
    erase
    -0.14
    xic
    -0.14
    POSITIVE LOGITS
    gie
    0.34
    oted
    0.33
    elow
    0.32
    wig
    0.30
    -ticket
    0.30
    gest
    0.29
    gies
    0.28
    amy
    0.28
    -picture
    0.27
    raph
    0.27
    Act Density 0.058%

    No Known Activations