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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential outcomes or situations that are contingent upon conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.02
    2:0.07
    3:0.14
    4:0.02
    5:0.06
    6:0.01
    7:0.03
    8:0.02
    9:0.01
    10:0.48
    11:0.02
    Negative Logits
     obedience
    -2.15
     obe
    -2.13
    rite
    -2.02
     respect
    -2.01
    }"
    -1.99
    venants
    -1.97
     obedient
    -1.92
    obbies
    -1.91
     Respect
    -1.86
    Strong
    -1.84
    POSITIVE LOGITS
     anytime
    3.01
     feas
    2.95
     potentially
    2.84
     anywhere
    2.63
     jeopardy
    2.57
    ivably
    2.57
     alternatively
    2.57
     future
    2.51
     someday
    2.48
     anybody
    2.37
    Act Density 0.418%

    No Known Activations