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

    Neuronpedia

    INDEX
    Explanations

    references to publishers and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.05
    3:0.06
    4:0.09
    5:0.02
    6:0.12
    7:0.30
    8:0.03
    9:0.03
    10:0.14
    11:0.08
    Negative Logits
    ophobic
    -1.55
    rous
    -1.46
    ophobia
    -1.44
    ewitness
    -1.42
    visor
    -1.41
     submer
    -1.39
     toast
    -1.39
     situational
    -1.38
    antry
    -1.35
     vis
    -1.33
    POSITIVE LOGITS
     Publishers
    1.73
     Digest
    1.50
     Publications
    1.46
     Enterprises
    1.46
     Norton
    1.44
     Toledo
    1.40
     Winds
    1.38
     Stafford
    1.37
     Caldwell
    1.37
     newspapers
    1.36
    Act Density 0.002%

    No Known Activations