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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a change or shift in something

    oai_token-act-pair · gpt-3.5-turbo

    references to changes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Crunch
    -0.74
    KK
    -0.74
    Cru
    -0.70
    aturdays
    -0.69
    GGGGGGGG
    -0.68
    linger
    -0.67
    EEEE
    -0.67
    lees
    -0.67
    ©¶æ¥µ
    -0.65
    Sure
    -0.65
    POSITIVE LOGITS
     favor
    0.88
     favour
    0.86
     fortunes
    0.85
     scenery
    0.84
     regards
    0.83
    version
    0.82
     situ
    0.82
    animate
    0.81
     circumstance
    0.78
     circumstances
    0.78
    Act Density 0.089%

    No Known Activations