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

    Neuronpedia

    INDEX
    Explanations

    contractions of the verb 'is'

    oai_token-act-pair · gpt-3.5-turbo

    negation statements, particularly the phrase "isn't."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     encounters
    -0.71
     hatch
    -0.69
    oning
    -0.65
    owan
    -0.64
     Species
    -0.62
     Oaks
    -0.61
     Mant
    -0.60
     LV
    -0.60
    ocaust
    -0.60
    fox
    -0.60
    POSITIVE LOGITS
    't
    1.32
    terness
    0.88
    ajor
    0.86
    NOT
    0.77
    rael
    0.76
    nai
    0.74
    TeX
    0.73
     hardly
    0.72
     indeed
    0.71
    ettings
    0.71
    Act Density 0.041%

    No Known Activations