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

    Neuronpedia

    INDEX
    Explanations

    words expressing authenticity and sincerity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UserScript
    -0.55
    pushFollow
    -0.55
    :]:
    -0.54
    Resumo
    -0.54
     kentang
    -0.54
    hdashline
    -0.54
     <>",
    -0.53
    :][
    -0.53
    #+#
    -0.53
    SPATH
    -0.52
    POSITIVE LOGITS
     truly
    0.97
     real
    0.95
     genuinely
    0.94
     actual
    0.91
     genuine
    0.89
     REAL
    0.88
    actual
    0.87
     realy
    0.86
    Truly
    0.84
    真正
    0.83
    Act Density 0.231%

    No Known Activations