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

    Neuronpedia

    INDEX
    Explanations

    negative phrases related to scale or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    НИК
    -0.59
    NOPQRST
    -0.58
     INTERESAR
    -0.55
     Villar
    -0.52
    madas
    -0.51
    pergillus
    -0.49
    AccessorTable
    -0.48
    Pill
    -0.48
    long
    -0.47
    aldi
    -0.47
    POSITIVE LOGITS
     الرياضيه
    0.72
    Portale
    0.67
     houſe
    0.66
     Efq
    0.64
    duled
    0.64
     ſmall
    0.64
    بوابة
    0.63
     Houſe
    0.63
    olesale
    0.62
     purpoſe
    0.61
    Act Density 0.280%

    No Known Activations