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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ownership or possession

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to individual agency and autonomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.89
    enos
    -0.71
    phal
    -0.66
    pired
    -0.65
    olen
    -0.65
    uador
    -0.64
    angled
    -0.62
    eus
    -0.59
    uba
    -0.59
    ocumented
    -0.59
    POSITIVE LOGITS
     situation
    0.89
     assumption
    0.84
     scenario
    0.83
    _.
    0.83
    !!!!
    0.82
     thing
    0.81
     option
    0.80
     anyways
    0.80
     timetable
    0.79
    .#
    0.79
    Act Density 0.562%

    No Known Activations