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

    Neuronpedia

    INDEX
    Explanations

    instances of destruction or damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igan
    -0.16
    /GPL
    -0.15
    ủng
    -0.15
    ania
    -0.15
    arov
    -0.14
    cop
    -0.14
    propri
    -0.14
    /board
    -0.14
    zyst
    -0.14
    cho
    -0.14
    POSITIVE LOGITS
    s
    0.19
    irez
    0.15
    umble
    0.15
    zman
    0.14
     Grade
    0.14
    vat
    0.14
     bes
    0.14
    _NV
    0.14
    udder
    0.13
    еÑĢж
    0.13
    Act Density 0.005%

    No Known Activations