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

    Neuronpedia

    INDEX
    Explanations

    references to component structures and their associated metadata in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oe
    -0.19
    (s
    -0.18
    Ñķ
    -0.18
    (es
    -0.17
    uggle
    -0.16
    er
    -0.16
    lets
    -0.15
    ãģ¾ãģ¾
    -0.15
    oi
    -0.15
    lijke
    -0.15
    POSITIVE LOGITS
    cape
    0.22
    heets
    0.22
    cales
    0.21
    aber
    0.20
    uits
    0.18
    ight
    0.18
    hips
    0.18
    avers
    0.18
    pectrum
    0.17
    kins
    0.17
    Act Density 0.244%

    No Known Activations