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

    Neuronpedia

    INDEX
    Explanations

    personal qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to identity and personal experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UCT
    -0.75
    ridges
    -0.67
    ollow
    -0.60
    Measure
    -0.58
    skirts
    -0.56
     miscarriage
    -0.56
    vier
    -0.54
    æ©Ł
    -0.54
    saf
    -0.53
    loads
    -0.52
    POSITIVE LOGITS
     be
    0.70
     become
    0.69
     are
    0.67
    Were
    0.67
    be
    0.65
     Beaver
    0.64
     ARE
    0.63
    ãĤ«
    0.63
    Be
    0.63
     Are
    0.62
    Act Density 0.255%

    No Known Activations