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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negation or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hasMoreElements
    -0.61
     AssemblyProduct
    -0.54
    libft
    -0.52
    ajuku
    -0.52
    RTCF
    -0.51
     Penh
    -0.51
     TType
    -0.50
    GrantedAuthority
    -0.50
    windowFixed
    -0.49
    gud
    -0.49
    POSITIVE LOGITS
     Савезне
    0.67
     actual
    0.65
    usermodel
    0.63
    pecto
    0.57
    Jîn
    0.57
     оригіналу
    0.57
     iconFacebook
    0.57
     intitulé
    0.56
     himo
    0.56
     actually
    0.55
    Act Density 0.303%

    No Known Activations