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

    Neuronpedia

    INDEX
    Explanations

    numeric values, including statistics and scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    208
    -0.17
    ulos
    -0.16
    cci
    -0.16
    ahn
    -0.16
    945
    -0.15
    ortho
    -0.15
    401
    -0.15
    837
    -0.15
    ales
    -0.14
    ieri
    -0.14
    POSITIVE LOGITS
    666
    0.23
    333
    0.22
    667
    0.22
    Ķ
    0.19
    ĶåĽŀ
    0.16
    endon
    0.16
    çĵľ
    0.16
    .Axis
    0.15
    urga
    0.15
    NodeType
    0.15
    Act Density 0.069%

    No Known Activations