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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential outcomes or consequences based on current trends or actions

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements regarding future events or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Annotations
    -0.62
     amazed
    -0.61
    LESS
    -0.61
     entertained
    -0.59
     contrasts
    -0.57
    schild
    -0.56
    ighters
    -0.55
    ictionary
    -0.55
    ;;;;;;;;
    -0.54
    erence
    -0.54
    POSITIVE LOGITS
     tomorrow
    1.02
     someday
    0.87
     sooner
    0.75
    mission
    0.74
     tonight
    0.72
     hereafter
    0.71
     sufficiently
    0.69
    missions
    0.68
     today
    0.68
    enough
    0.68
    Act Density 0.265%

    No Known Activations