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

    Neuronpedia

    INDEX
    Explanations

    elements related to proximity and arrival

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IDENTAL
    -0.43
     failing
    -0.42
     dis
    -0.42
    ("]");
    -0.42
     Wo
    -0.42
    woon
    -0.41
     filled
    -0.40
    '):
    -0.40
     ar
    -0.40
     fails
    -0.40
    POSITIVE LOGITS
     emerge
    1.03
     emerges
    1.02
     afterward
    0.87
     afterwards
    0.82
     emerged
    0.82
     Afterwards
    0.77
     exit
    0.76
     émer
    0.74
     Afterward
    0.73
    argout
    0.72
    Act Density 0.186%

    No Known Activations