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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the absence of something or refer to conditions lacking certain elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    localhost
    -0.49
     Port
    -0.48
     Orth
    -0.48
     Fide
    -0.46
    WriteBarrier
    -0.45
     Bun
    -0.45
    bay
    -0.45
     Kark
    -0.45
     edward
    -0.44
    HOM
    -0.44
    POSITIVE LOGITS
     ausencia
    0.62
     sienta
    0.62
     cuerdas
    0.57
     playera
    0.56
     sandalias
    0.54
     Савезне
    0.53
     rodillas
    0.52
     acuarela
    0.52
     vectoriales
    0.51
     betweenstory
    0.51
    Act Density 0.207%

    No Known Activations