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

    Neuronpedia

    INDEX
    Explanations

    words related to communication, such as "signal."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to signaling in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erenn
    -0.74
    sm
    -0.73
    venge
    -0.72
    uum
    -0.71
    yright
    -0.71
    jury
    -0.70
    spell
    -0.68
    amily
    -0.66
     Roof
    -0.64
    ighth
    -0.64
    POSITIVE LOGITS
     signals
    1.04
     handlers
    1.00
     emanating
    0.99
     handler
    0.95
     signal
    0.94
     reinforcement
    0.84
     emitted
    0.83
     blocker
    0.83
     signaling
    0.82
     overload
    0.82
    Act Density 0.038%

    No Known Activations