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

    Neuronpedia

    INDEX
    Explanations

    general expressions of curiosity or contemplation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theit
    -0.55
    Legenda
    -0.55
     intptr
    -0.54
    issy
    -0.54
    thalten
    -0.51
    ruik
    -0.50
    torta
    -0.49
    찮
    -0.48
    acterium
    -0.47
    secutions
    -0.47
    POSITIVE LOGITS
     viewer
    0.77
     reader
    0.72
     viewers
    0.70
     rooting
    0.67
     readers
    0.63
     penonton
    0.62
    TagMode
    0.61
     espectador
    0.61
     зри
    0.61
    readers
    0.60
    Act Density 0.223%

    No Known Activations