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

    Neuronpedia

    INDEX
    Explanations

    references to images or visuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    гин
    -0.49
    Imaginary
    -0.49
     fueled
    -0.49
     Imagine
    -0.47
    ereich
    -0.47
     Imagin
    -0.47
     Cle
    -0.46
    IVOS
    -0.45
     imaginations
    -0.44
     darte
    -0.43
    POSITIVE LOGITS
     itſelf
    0.74
    ſelves
    0.73
     myſelf
    0.71
    ſelf
    0.69
     Houſe
    0.68
     pleaſure
    0.68
     betweenstory
    0.67
     quæ
    0.65
     Efq
    0.65
     leaſt
    0.64
    Act Density 0.264%

    No Known Activations