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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "see" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "you can see."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disposal
    -0.66
    inals
    -0.64
    ortunately
    -0.63
     resil
    -0.63
    cycl
    -0.63
    %]
    -0.60
    orne
    -0.60
    onies
    -0.60
     fielded
    -0.59
     perpetrated
    -0.58
    POSITIVE LOGITS
    seeing
    0.87
    ibly
    0.80
    ById
    0.78
    lift
    0.78
    ocular
    0.75
     eye
    0.75
    eva
    0.75
    erala
    0.70
    ibility
    0.70
    IRT
    0.70
    Act Density 0.044%

    No Known Activations