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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and related verbs indicating hypothetical scenarios or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    repeated first-person pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quartered
    -0.76
    mud
    -0.65
    Ts
    -0.65
    IOR
    -0.62
     Bearing
    -0.62
    bats
    -0.61
    MENTS
    -0.60
    interstitial
    -0.60
    folios
    -0.59
     Emanuel
    -0.58
    POSITIVE LOGITS
     succeed
    0.86
     weren
    0.83
    're
    0.77
     happen
    0.76
     were
    0.75
     someday
    0.73
     grap
    0.72
     fail
    0.72
    lisher
    0.69
     wanna
    0.69
    Act Density 0.145%

    No Known Activations