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

    Neuronpedia

    INDEX
    Explanations

    words related to communication or information transfer, particularly technical terms such as 'signal'

    oai_token-act-pair · gpt-3.5-turbo

    words related to signals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amily
    -0.78
    sm
    -0.74
    illac
    -0.68
    iler
    -0.68
    vre
    -0.67
    uum
    -0.66
    ski
    -0.66
    erenn
    -0.66
    eenth
    -0.65
    frey
    -0.65
    POSITIVE LOGITS
     signals
    0.92
     handlers
    0.91
     signal
    0.80
     emanating
    0.79
     handler
    0.78
    eering
    0.77
     strength
    0.75
     reinforcement
    0.73
     strengths
    0.73
     signaling
    0.72
    Act Density 0.027%

    No Known Activations