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

    Neuronpedia

    INDEX
    Explanations

    words related to communication signals or cues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    sm
    -0.71
    vre
    -0.68
    amily
    -0.66
    cember
    -0.66
    ski
    -0.65
    endor
    -0.63
     Roof
    -0.63
    shop
    -0.63
    iler
    -0.63
    ositories
    -0.62
    POSITIVE LOGITS
     handlers
    0.94
     signals
    0.89
     signal
    0.80
     handler
    0.80
     emanating
    0.79
    eering
    0.79
     reinforcement
    0.78
     signaling
    0.77
     strength
    0.76
     overload
    0.74
    Act Density 0.022%

    No Known Activations