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

    Neuronpedia

    INDEX
    Explanations

    words associated with significant values, positions, or political themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adin
    -0.18
    %C
    -0.16
    ournals
    -0.14
    utow
    -0.14
     ribbon
    -0.14
    oxy
    -0.14
     Ribbon
    -0.14
    ££
    -0.14
     imagination
    -0.14
     wn
    -0.13
    POSITIVE LOGITS
    à¥ĭल
    0.15
    orget
    0.15
    .Navigator
    0.15
    '=>['
    0.14
    edo
    0.14
    ean
    0.14
    nict
    0.14
    .lab
    0.14
    USES
    0.14
    ONTAL
    0.13
    Act Density 0.007%

    No Known Activations