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

    Neuronpedia

    INDEX
    Explanations

    references to indiscriminate actions or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rite
    -0.88
    Ctrl
    -0.68
     Nightmares
    -0.67
     Illusion
    -0.67
    lda
    -0.67
    ovember
    -0.66
    OPLE
    -0.63
     Theater
    -0.62
     Archdemon
    -0.62
     Skydragon
    -0.62
    POSITIVE LOGITS
    inately
    1.17
    inatory
    0.86
    inant
    0.85
    acies
    0.84
    cest
    0.83
    ately
    0.82
    rative
    0.81
    acious
    0.77
    inate
    0.77
    inating
    0.76
    Act Density 0.052%

    No Known Activations