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

    Neuronpedia

    INDEX
    Explanations

    words related to deception and disguise

    oai_token-act-pair · gpt-3.5-turbo

    instances of the syllable "gu" in varied contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cling
    -0.76
    croft
    -0.75
     Spectrum
    -0.72
    rings
    -0.69
    hower
    -0.69
    riad
    -0.68
    cycle
    -0.67
    HAEL
    -0.65
    ŃĶ
    -0.64
    âĶģ
    -0.61
    POSITIVE LOGITS
    pta
    1.16
    ilty
    1.14
    idelines
    1.13
    errilla
    1.09
    arding
    1.09
    cci
    1.08
    vernment
    1.05
    arant
    1.03
    inea
    1.01
    ests
    1.01
    Act Density 0.021%

    No Known Activations