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

    Neuronpedia

    INDEX
    Explanations

    personal statements or opinions

    oai_token-act-pair · gpt-3.5-turbo

    personal pronouns and expressions of personal opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Meadow
    -0.76
    iens
    -0.74
     Gulf
    -0.67
     prophets
    -0.64
     Freeman
    -0.64
     Annotations
    -0.63
     Clintons
    -0.62
     Roses
    -0.61
     TIM
    -0.61
     Apostles
    -0.59
    POSITIVE LOGITS
     Personally
    0.94
    etheless
    0.92
    odox
    0.89
    Personally
    0.85
     minded
    0.77
    asured
    0.77
    entimes
    0.74
     speaking
    0.74
    istical
    0.73
     inclined
    0.71
    Act Density 0.007%

    No Known Activations