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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "or" and related conjunctions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unw
    -0.19
     fit
    -0.16
    aque
    -0.16
    /or
    -0.16
    orra
    -0.16
    ico
    -0.16
    castle
    -0.15
     Sy
    -0.15
     undes
    -0.15
    coli
    -0.15
    POSITIVE LOGITS
     Bust
    0.17
    xba
    0.17
    agal
    0.16
    ATHER
    0.15
    ator
    0.15
    æĪIJ人
    0.15
    ourke
    0.15
    xaa
    0.15
     BCHP
    0.15
    CHAN
    0.14
    Act Density 0.081%

    No Known Activations