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

    Neuronpedia

    INDEX
    Explanations

    references to individuals being highlighted or singled out in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.01
    2:0.07
    3:0.06
    4:0.07
    5:0.03
    6:0.03
    7:0.42
    8:0.03
    9:0.04
    10:0.06
    11:0.08
    Negative Logits
    loop
    -1.59
    gif
    -1.44
    hyd
    -1.40
     bonds
    -1.37
     decay
    -1.36
    oppable
    -1.36
    ramids
    -1.33
    iland
    -1.30
    conserv
    -1.28
    rio
    -1.24
    POSITIVE LOGITS
     singled
    1.78
    grave
    1.77
    agher
    1.59
    zinski
    1.48
    ��
    1.46
     scorn
    1.45
     unfairly
    1.41
    bies
    1.40
     collaborators
    1.39
     exceptions
    1.38
    Act Density 0.002%

    No Known Activations