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

    Neuronpedia

    INDEX
    Explanations

    questions including the phrase "Have you ever"

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal experiences or reflective questions about life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Versions
    -0.72
    ]).
    -0.69
    hawks
    -0.66
     Annex
    -0.65
     ASC
    -0.64
     ])
    -0.64
     ranges
    -0.63
    hod
    -0.63
     inclusive
    -0.63
     precedence
    -0.62
    POSITIVE LOGITS
     wondering
    1.11
     wondered
    1.03
     tempted
    0.99
     stumble
    0.97
     accidentally
    0.93
     contemplating
    0.90
     yourself
    0.89
     browsing
    0.88
     fantas
    0.85
     stumbled
    0.84
    Act Density 0.291%

    No Known Activations