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

    Neuronpedia

    INDEX
    Explanations

    references to belief systems and their implications on behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odie
    -0.16
    ALA
    -0.15
    .tie
    -0.14
    æŁ´
    -0.14
    ala
    -0.14
    ibox
    -0.14
     gü
    -0.14
    xAA
    -0.14
    enos
    -0.13
    acci
    -0.13
    POSITIVE LOGITS
     gesture
    0.16
    ól
    0.16
    ove
    0.15
    ego
    0.15
    rena
    0.15
    479
    0.14
    richt
    0.14
    sheets
    0.14
    ÑħÑĥ
    0.14
    ICO
    0.13
    Act Density 0.115%

    No Known Activations