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

    Neuronpedia

    INDEX
    Explanations

    mathematical constructs and relationships in graphs and distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ============================================================================↵
    -0.16
    639
    -0.15
    ritable
    -0.14
     hrom
    -0.14
    icontrol
    -0.14
    SError
    -0.14
    oram
    -0.13
    ickerView
    -0.13
    heimer
    -0.13
    swick
    -0.13
    POSITIVE LOGITS
    anja
    0.17
    oud
    0.16
    Content
    0.15
    stoup
    0.15
    ziel
    0.14
    ittings
    0.14
     no
    0.14
    .high
    0.14
    å£
    0.14
    alo
    0.14
    Act Density 0.122%

    No Known Activations