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

    Neuronpedia

    INDEX
    Explanations

    instructions or calls to action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.06
    2:0.06
    3:0.11
    4:0.12
    5:0.07
    6:0.06
    7:0.06
    8:0.09
    9:0.09
    10:0.04
    11:0.07
    Negative Logits
     heav
    -1.96
    .–
    -1.88
     originally
    -1.79
    ;;;;
    -1.79
     stiff
    -1.76
     indeed
    -1.74
    ;;
    -1.73
     otherwise
    -1.72
     simpler
    -1.72
     actually
    -1.71
    POSITIVE LOGITS
    anamo
    2.85
    iatric
    2.24
    icum
    2.17
    onds
    1.97
    adel
    1.95
    ohyd
    1.93
    acent
    1.90
    forts
    1.90
    phrine
    1.89
    culosis
    1.88
    Act Density 0.001%

    No Known Activations