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

    Neuronpedia

    INDEX
    Explanations

    instances of the ellipsis or pauses in text communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SC
    -0.16
    esh
    -0.15
    rell
    -0.15
    sets
    -0.15
    hit
    -0.15
    anto
    -0.15
    tam
    -0.14
    qv
    -0.14
    nam
    -0.14
    æĢ
    -0.14
    POSITIVE LOGITS
    lick
    0.18
    ¹
    0.15
    blick
    0.15
    综åIJĪ
    0.14
    zing
    0.14
    oldur
    0.13
    etc
    0.13
    Ïħνα
    0.13
    lij
    0.13
     underestimated
    0.13
    Act Density 0.027%

    No Known Activations