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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a position or sentiment regarding political support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.09
    2:0.08
    3:0.09
    4:0.07
    5:0.08
    6:0.08
    7:0.09
    8:0.07
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
     Horus
    -2.94
     Leap
    -2.87
     Cortana
    -2.62
     Companion
    -2.61
     Navigation
    -2.60
     Throne
    -2.58
     Vive
    -2.55
     Chapters
    -2.52
     Beacon
    -2.50
     Ramsay
    -2.50
    POSITIVE LOGITS
    icut
    3.17
    rich
    3.05
    ritch
    2.93
    SourceFile
    2.92
    berman
    2.89
    paren
    2.85
    gew
    2.81
    olester
    2.80
    ieves
    2.75
    maxwell
    2.70
    Act Density 0.000%

    No Known Activations