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

    Neuronpedia

    INDEX
    Explanations

    mentions or discussions related to projections or projected outcomes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to projections and forecasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.93
    gel
    -0.77
    ldom
    -0.74
    gart
    -0.74
    oho
    -0.72
    anguages
    -0.72
    turn
    -0.71
    baum
    -0.71
    ste
    -0.70
    gently
    -0.70
    POSITIVE LOGITS
     projections
    0.95
     projection
    0.89
     upwards
    0.83
     projecting
    0.81
     outward
    0.77
     Archdemon
    0.77
     upward
    0.71
     ceilings
    0.70
     projected
    0.69
     downwards
    0.68
    Act Density 0.020%

    No Known Activations