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

    Neuronpedia

    INDEX
    Explanations

    references to data or applications, particularly those related to potential data leaks or vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.22
    1:0.19
    2:0.03
    3:0.06
    4:0.04
    5:0.03
    6:0.07
    7:0.13
    8:0.03
    9:0.03
    10:0.08
    11:0.04
    Negative Logits
     Heller
    -3.49
     Atom
    -2.86
     Byrd
    -2.83
     Ukrain
    -2.71
     McCarthy
    -2.66
     Feldman
    -2.59
    rina
    -2.54
     homophobic
    -2.52
    obyl
    -2.49
     posit
    -2.47
    POSITIVE LOGITS
    une
    4.77
    UNE
    4.22
    uning
    3.71
    unes
    3.67
     sand
    3.05
    cients
    2.99
    uned
    2.85
    acci
    2.81
     sequ
    2.76
    imus
    2.75
    Act Density 0.001%

    No Known Activations