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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombat
    -0.89
    lete
    -0.87
    ife
    -0.85
    cies
    -0.83
    iak
    -0.82
    iya
    -0.78
    ocaust
    -0.78
    ament
    -0.78
    atches
    -0.76
    emale
    -0.76
    POSITIVE LOGITS
     someday
    1.24
     subconscious
    0.80
     SOME
    0.75
     even
    0.74
     sooner
    0.69
     tempted
    0.68
     unsurprisingly
    0.66
     accidentally
    0.66
     misunder
    0.66
     kidding
    0.66
    Act Density 0.039%

    No Known Activations