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

    Neuronpedia

    INDEX
    Explanations

    the word "signal" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of signals, particularly in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amily
    -0.84
    ucket
    -0.76
    ski
    -0.75
    ean
    -0.74
    sm
    -0.74
    endor
    -0.73
    cember
    -0.71
    erity
    -0.71
    eenth
    -0.69
    hur
    -0.68
    POSITIVE LOGITS
     signals
    1.04
     handlers
    0.92
     signal
    0.90
     flares
    0.81
     emanating
    0.81
     handler
    0.80
     transmissions
    0.79
     signaling
    0.76
     Signal
    0.76
     signatures
    0.75
    Act Density 0.033%

    No Known Activations