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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain text structures indicating emphasis or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iol
    -0.17
    eki
    -0.15
    inator
    -0.14
    ErrorException
    -0.14
    forgettable
    -0.14
    esel
    -0.13
    ieurs
    -0.13
    unci
    -0.13
    pei
    -0.13
    ISOString
    -0.13
    POSITIVE LOGITS
     hence
    0.17
     ведÑĮ
    0.16
    orton
    0.15
     thereby
    0.15
    åĨµ
    0.15
    warts
    0.15
    athers
    0.14
    amil
    0.14
     something
    0.14
    boom
    0.13
    Act Density 0.106%

    No Known Activations