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

    Neuronpedia

    INDEX
    Explanations

    connections and transitions in discourse, particularly through the use of conjunctions and conditional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -fw
    -0.15
    advance
    -0.14
    916
    -0.14
    contexts
    -0.14
    dney
    -0.14
    بÙĦ
    -0.14
    blr
    -0.14
    plements
    -0.14
    licative
    -0.14
     ("<
    -0.14
    POSITIVE LOGITS
     cá»ij
    0.16
    iah
    0.14
    taÅŁ
    0.14
    izio
    0.14
    ÎIJ
    0.14
    _ENCODING
    0.13
    lernen
    0.13
    orman
    0.13
    ound
    0.13
    oucher
    0.13
    Act Density 0.004%

    No Known Activations