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

    Neuronpedia

    INDEX
    Explanations

    names of journalists and organizations involved in reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.01
    3:0.03
    4:0.33
    5:0.11
    6:0.05
    7:0.01
    8:0.08
    9:0.25
    10:0.01
    11:0.01
    Negative Logits
    nil
    -2.25
     advis
    -2.22
    76561
    -2.17
    Naz
    -1.98
    bleacher
    -1.89
    assic
    -1.88
     slumped
    -1.85
     plummeted
    -1.82
    omorphic
    -1.80
     confir
    -1.78
    POSITIVE LOGITS
     Allows
    1.95
     Another
    1.87
    annels
    1.82
    INTON
    1.81
     Images
    1.77
    letters
    1.77
    aho
    1.74
     Photos
    1.73
     Alternatively
    1.73
    plom
    1.73
    Act Density 0.003%

    No Known Activations