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

    Neuronpedia

    INDEX
    Explanations

    the word "besides" and related phrases indicating additional information or considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behalf
    -0.18
    abyrin
    -0.16
    zone
    -0.15
    leme
    -0.14
    vp
    -0.14
    osing
    -0.14
    nt
    -0.14
    thro
    -0.13
    nad
    -0.13
    up
    -0.13
    POSITIVE LOGITS
    jÅ¡ÃŃ
    0.17
    .Dispatcher
    0.16
     aside
    0.16
    amento
    0.16
     Apart
    0.15
    ordinal
    0.15
    å¤ķ
    0.15
    abox
    0.15
    ÌĢ
    0.15
    ÏģοÏį
    0.15
    Act Density 0.018%

    No Known Activations