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

    Neuronpedia

    INDEX
    Explanations

    unique names, terms, or brands that are specific to certain contexts or fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    'nin
    -0.18
    lier
    -0.18
    beits
    -0.17
    (s
    -0.16
    èĹ
    -0.16
    liness
    -0.16
    ering
    -0.16
    bed
    -0.16
    placer
    -0.15
    bate
    -0.15
    POSITIVE LOGITS
    es
    0.36
    (es
    0.35
    tures
    0.32
    s
    0.31
    plorer
    0.29
    xed
    0.28
    cellent
    0.24
    xes
    0.24
    avier
    0.24
    ional
    0.24
    Act Density 0.098%

    No Known Activations