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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exclusivity and emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.09
    3:0.07
    4:0.09
    5:0.08
    6:0.08
    7:0.07
    8:0.07
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
     Oracle
    -2.51
     Matter
    -2.51
     listeners
    -2.46
     geometry
    -2.45
     spectators
    -2.43
     Verse
    -2.42
     Alternative
    -2.40
     Elect
    -2.40
     Judges
    -2.37
     Alexa
    -2.37
    POSITIVE LOGITS
    jong
    3.06
    igun
    2.92
    kefeller
    2.83
    orea
    2.80
     Rebell
    2.75
    irst
    2.70
    cot
    2.68
    Sov
    2.65
    arthy
    2.63
    �
    2.61
    Act Density 0.000%

    No Known Activations