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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causality or a sequence of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to sequences or systems of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alty
    -0.81
    ayson
    -0.79
    dad
    -0.77
    mson
    -0.74
    ij士
    -0.73
    bowl
    -0.72
    atorium
    -0.70
    acious
    -0.69
    ESPN
    -0.68
    full
    -0.68
    POSITIVE LOGITS
     sorts
    0.85
     events
    0.78
     interconnected
    0.73
     alternating
    0.72
     communication
    0.69
     molecules
    0.68
     mutual
    0.66
     attrition
    0.66
     contacts
    0.66
     disparate
    0.65
    Act Density 0.139%

    No Known Activations