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

    Neuronpedia

    INDEX
    Explanations

    words related to communication or information transmission

    oai_token-act-pair · gpt-3.5-turbo

    references to signaling mechanisms or signals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amily
    -0.81
    ski
    -0.80
    vre
    -0.77
    sm
    -0.75
    endor
    -0.72
    eenth
    -0.71
    uum
    -0.68
    iler
    -0.68
    frey
    -0.68
    enne
    -0.67
    POSITIVE LOGITS
     signals
    0.94
     handlers
    0.88
     signal
    0.79
     signaling
    0.78
     Signal
    0.77
     emanating
    0.76
    eering
    0.74
     handler
    0.73
     transmissions
    0.72
     signalling
    0.71
    Act Density 0.028%

    No Known Activations