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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating equality or similarity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "equally."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LD
    -0.81
     Hol
    -0.72
     Clin
    -0.68
     Lip
    -0.68
     Banner
    -0.67
     Archives
    -0.67
     Coffee
    -0.67
    ocene
    -0.67
     Hockey
    -0.66
     Rider
    -0.65
    POSITIVE LOGITS
     equally
    1.03
    equal
    0.84
    ivari
    0.82
    itably
    0.78
     situated
    0.78
     spaced
    0.77
    inguishable
    0.75
     minded
    0.75
    visory
    0.75
    ministic
    0.74
    Act Density 0.004%

    No Known Activations