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

    Neuronpedia

    INDEX
    Explanations

    references to kernel-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     représenté
    -0.86
     coû
    -0.83
     olev
    -0.80
    KommentareTeilen
    -0.79
     bonté
    -0.76
     republics
    -0.75
     andato
    -0.75
     saira
    -0.75
     autoradio
    -0.75
     cucchia
    -0.75
    POSITIVE LOGITS
     maintain
    0.67
    kernel
    0.63
     kernel
    0.61
    Maintain
    0.59
     Maintain
    0.58
     preserve
    0.57
     von
    0.56
     mod
    0.56
     mask
    0.55
    ent
    0.54
    Act Density 0.111%

    No Known Activations