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

    Neuronpedia

    INDEX
    Explanations

    extreme adjectives that convey a sense of significance or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃĸL
    -0.15
    ãĥįãĥ«
    -0.15
    Ãłn
    -0.15
    ÑĢем
    -0.14
     fallback
    -0.14
    isex
    -0.14
    ãģŁãĤģãģ®
    -0.14
    apos
    -0.14
    nem
    -0.13
    409
    -0.13
    POSITIVE LOGITS
     amount
    0.37
     amounts
    0.36
    amount
    0.31
     Amount
    0.30
     levels
    0.28
    Amount
    0.26
    ly
    0.23
    ingly
    0.22
    _amount
    0.22
     proportions
    0.22
    Act Density 0.162%

    No Known Activations