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

    Neuronpedia

    INDEX
    Explanations

    cones or cone-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to "cones"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.80
    ERAL
    -0.76
    Ö¼
    -0.69
    EEK
    -0.69
    ALK
    -0.69
    Known
    -0.67
    RESULTS
    -0.67
    Imm
    -0.67
    EMS
    -0.67
    ð
    -0.67
    POSITIVE LOGITS
     cone
    1.64
     cones
    1.38
    cone
    1.22
    otine
    0.85
     disg
    0.77
    pole
    0.76
     crus
    0.76
    xon
    0.74
     shaped
    0.73
     lobe
    0.73
    Act Density 0.008%

    No Known Activations