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

    Neuronpedia

    INDEX
    Explanations

    themes of transformation and identity shifts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '=>"
    -0.15
    '=>['
    -0.14
    rych
    -0.14
     Tul
    -0.14
     Thom
    -0.13
     Maurice
    -0.13
     Ticaret
    -0.13
     Tamb
    -0.13
     Sho
    -0.13
    uzey
    -0.13
    POSITIVE LOGITS
     transformation
    0.73
     transform
    0.71
    transform
    0.69
     Transformation
    0.67
     transformations
    0.65
     Transform
    0.65
    trans
    0.64
    -transform
    0.64
     transforms
    0.63
    -trans
    0.63
    Act Density 0.065%

    No Known Activations