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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and words indicating time or commonality in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abh
    -0.15
     jobject
    -0.15
    _strike
    -0.14
    .loggedIn
    -0.14
    imedia
    -0.14
     foul
    -0.13
    ikan
    -0.13
     Duy
    -0.13
    ιθ
    -0.13
    apel
    -0.13
    POSITIVE LOGITS
    pite
    0.16
    /lic
    0.15
    AMIL
    0.15
    anko
    0.14
    ients
    0.14
    akens
    0.14
    efa
    0.13
    rens
    0.13
     Reform
    0.13
    erm
    0.13
    Act Density 0.010%

    No Known Activations