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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to being unable to see or perceive

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being "blind," both literally and metaphorically

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xit
    -0.94
     Occupations
    -0.92
    AIN
    -0.72
    CE
    -0.72
    ickr
    -0.72
    ILY
    -0.70
    DN
    -0.70
    OPLE
    -0.69
    ICAN
    -0.69
    OTHER
    -0.66
    POSITIVE LOGITS
    blind
    1.38
     blind
    1.20
    sight
    1.09
    fold
    1.09
    sided
    1.01
    ibility
    0.98
     Blind
    0.92
     blinded
    0.89
    ingly
    0.89
    sighted
    0.85
    Act Density 0.011%

    No Known Activations