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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating probability or likelihood

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating probability or likelihood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gado
    -0.81
    elta
    -0.79
    zeb
    -0.79
    entric
    -0.77
    ente
    -0.76
    hips
    -0.76
    inth
    -0.76
    elt
    -0.74
    uart
    -0.74
    ometimes
    -0.74
    POSITIVE LOGITS
     underestimate
    0.80
     underest
    0.79
     culprit
    0.73
     releg
    0.72
     linem
    0.71
     overest
    0.70
    cffff
    0.67
     underestimated
    0.67
     elector
    0.66
     inference
    0.65
    Act Density 0.036%

    No Known Activations