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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate familiarity or personal experience with a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.03
    2:0.05
    3:0.24
    4:0.02
    5:0.08
    6:0.01
    7:0.10
    8:0.02
    9:0.02
    10:0.31
    11:0.02
    Negative Logits
    redients
    -2.24
    enburg
    -1.90
    "}],"
    -1.86
    %.
    -1.86
    effic
    -1.81
    KO
    -1.74
    ô
    -1.68
    Stop
    -1.68
    Percent
    -1.66
    elfth
    -1.66
    POSITIVE LOGITS
     slightest
    3.46
     bothered
    2.52
     knows
    2.37
     anything
    2.32
     acquaintance
    2.32
     EVER
    2.31
     ANY
    2.28
     nor
    2.28
     ever
    2.24
    anything
    2.21
    Act Density 0.117%

    No Known Activations