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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific names in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.40
    2:0.02
    3:0.01
    4:0.01
    5:0.25
    6:0.04
    7:0.01
    8:0.03
    9:0.07
    10:0.03
    11:0.01
    Negative Logits
     horizont
    -1.92
     gravity
    -1.84
     srfAttach
    -1.76
    theless
    -1.73
     weap
    -1.73
     nostalg
    -1.72
     horr
    -1.70
     glam
    -1.70
     naughty
    -1.69
     boots
    -1.65
    POSITIVE LOGITS
    enei
    2.85
    iken
    2.78
    ribe
    2.56
    ickson
    2.36
    acas
    2.34
    ajo
    2.33
    ilon
    2.32
    eria
    2.31
    olulu
    2.29
    raq
    2.29
    Act Density 0.302%

    No Known Activations