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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the usage and regulation of resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toi
    -0.17
    tran
    -0.17
    ships
    -0.16
    ../../../
    -0.16
    ross
    -0.16
    raz
    -0.15
    hound
    -0.15
    .nz
    -0.15
    ÅŁ
    -0.15
    гÑĥ
    -0.15
    POSITIVE LOGITS
    fully
    0.21
    FUL
    0.17
    ful
    0.17
    full
    0.17
    able
    0.17
    krom
    0.16
    -bodied
    0.15
    ÑģÑĮого
    0.14
    ëŁī
    0.14
    fulness
    0.14
    Act Density 0.081%

    No Known Activations