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

    Neuronpedia

    INDEX
    Explanations

    phrases that signify surpassing or exceeding expectations within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipt
    -0.15
    udu
    -0.14
    ÑĨеÑĢ
    -0.14
     Coupons
    -0.14
    createFrom
    -0.13
    ÙĨاد
    -0.13
    roys
    -0.13
     ÑģкладÑĥ
    -0.13
     thừa
    -0.13
    imap
    -0.13
    POSITIVE LOGITS
     mere
    0.44
     merely
    0.41
     simply
    0.31
    mere
    0.31
     just
    0.29
     пÑĢоÑģÑĤо
    0.28
     juste
    0.26
    åıªæĺ¯
    0.24
    ä»ħ
    0.24
     simplement
    0.24
    Act Density 0.048%

    No Known Activations