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

    Neuronpedia

    INDEX
    Explanations

    references to escaping or fleeing from different situations or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to escape or fleeing from dangerous or adverse situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.98
    yip
    -0.79
    Assistant
    -0.76
    yi
    -0.74
    Fax
    -0.70
    paper
    -0.69
    arget
    -0.67
    android
    -0.66
    reads
    -0.65
    ieth
    -0.65
    POSITIVE LOGITS
     clut
    0.98
     confines
    0.97
     boredom
    0.90
     obscurity
    0.83
     wilderness
    0.83
     wrath
    0.80
     bounds
    0.80
     heights
    0.78
     temptation
    0.75
     captivity
    0.75
    Act Density 0.214%

    No Known Activations