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

    Neuronpedia

    INDEX
    Explanations

    negative phrases or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.85
    DockStyle
    -0.80
     Varanasi
    -0.70
     imprimé
    -0.70
    MessageInfo
    -0.69
     Tacitus
    -0.69
     Flanagan
    -0.67
    Portály
    -0.66
    发表于
    -0.65
     depositors
    -0.64
    POSITIVE LOGITS
     quite
    0.73
    也不是
    0.68
     becoming
    0.68
    колко
    0.66
     صوتيه
    0.66
     McQu
    0.63
     været
    0.63
     setIs
    0.63
    并不是
    0.62
    withstanding
    0.62
    Act Density 0.169%

    No Known Activations