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

    Neuronpedia

    INDEX
    Explanations

    references to body parts and injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.16
    1:0.02
    2:0.16
    3:0.05
    4:0.06
    5:0.04
    6:0.09
    7:0.02
    8:0.10
    9:0.05
    10:0.08
    11:0.11
    Negative Logits
    rupulous
    -1.81
    oaded
    -1.75
    uggest
    -1.64
    entious
    -1.63
    ��
    -1.56
    ocious
    -1.51
    cipled
    -1.50
    etically
    -1.49
    pmwiki
    -1.48
    uct
    -1.48
    POSITIVE LOGITS
    stretched
    1.69
     gravity
    1.48
     cane
    1.46
     etc
    1.44
     respectively
    1.42
     crest
    1.41
     radius
    1.38
     pyramid
    1.36
     compass
    1.35
     flats
    1.34
    Act Density 0.082%

    No Known Activations