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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical objects, particularly rods and cones

    oai_token-act-pair · gpt-3.5-turbo

    references to rods and cones, often related to vision or physical objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eanor
    -0.76
    ĵĺ
    -0.66
    pants
    -0.64
     antioxid
    -0.63
    irgin
    -0.62
     achie
    -0.62
    olitan
    -0.62
     Columb
    -0.61
     conscious
    -0.60
    arily
    -0.60
    POSITIVE LOGITS
     rods
    0.96
    erick
    0.95
     rod
    0.91
    icularly
    0.78
    rig
    0.77
    icular
    0.75
    lings
    0.72
    backs
    0.72
    aways
    0.71
     pier
    0.70
    Act Density 0.022%

    No Known Activations