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

    Neuronpedia

    INDEX
    Explanations

    quantities and numerical values related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.19
    ourn
    -0.16
    enas
    -0.16
    bler
    -0.15
    uros
    -0.15
    arias
    -0.15
    èį
    -0.15
    azer
    -0.15
    аниÑĨ
    -0.14
    aeper
    -0.14
    POSITIVE LOGITS
    orman
    0.17
    esto
    0.15
     suck
    0.15
    ittle
    0.15
     Barbar
    0.14
     Consumers
    0.14
    este
    0.14
    iamond
    0.14
    OMET
    0.14
    PRS
    0.14
    Act Density 0.107%

    No Known Activations