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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant life events or circumstances

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to life-saving actions or critical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -1.06
    Ey
    -0.88
    vous
    -0.84
    aye
    -0.82
    BLIC
    -0.74
    jab
    -0.73
    soDeliveryDate
    -0.73
    gew
    -0.73
    Invalid
    -0.73
    warn
    -0.72
    POSITIVE LOGITS
     ecstasy
    0.79
     solitude
    0.79
     expectancy
    0.77
     contemplation
    0.77
     agony
    0.72
     breathed
    0.72
     exile
    0.70
     Drain
    0.69
     captivity
    0.68
    conservancy
    0.68
    Act Density 0.298%

    No Known Activations