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

    Neuronpedia

    INDEX
    Explanations

    HTML and XML structural elements and tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     breeding
    -0.16
     Pens
    -0.15
    erd
    -0.15
     bomb
    -0.15
    ookie
    -0.15
    acci
    -0.15
     Corner
    -0.14
     depress
    -0.14
    bar
    -0.14
     Steering
    -0.14
    POSITIVE LOGITS
    hower
    0.18
    UTILITY
    0.17
    arel
    0.16
    èĵ
    0.16
    inherits
    0.16
    utdown
    0.15
    .ul
    0.15
    atri
    0.15
    resse
    0.15
    gaard
    0.15
    Act Density 0.024%

    No Known Activations