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

    Neuronpedia

    INDEX
    Explanations

    the word "besides" and its variations to identify additional information or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    505
    -0.15
    ëĪĦ
    -0.15
    imals
    -0.14
    leans
    -0.14
    koa
    -0.14
    adolu
    -0.13
    лоÑĩ
    -0.13
    ÑĢаÑĤ
    -0.13
     Amen
    -0.13
    tober
    -0.13
    POSITIVE LOGITS
     being
    0.17
    azen
    0.16
    ahoo
    0.16
    _concat
    0.16
     cast
    0.15
    cast
    0.15
     Rubin
    0.14
     dcc
    0.14
     Chief
    0.14
    å¤ķ
    0.14
    Act Density 0.012%

    No Known Activations