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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing repetition or emphasis in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baugh
    -0.16
    ierce
    -0.15
    thon
    -0.14
    ewise
    -0.14
    еÑī
    -0.13
    terror
    -0.13
    ÄĽÅ¾
    -0.13
    theless
    -0.13
    wig
    -0.13
    جÙĩ
    -0.13
    POSITIVE LOGITS
    qe
    0.16
    clc
    0.16
    enty
    0.15
    OSP
    0.15
    bcc
    0.15
    -called
    0.14
     Moy
    0.14
    jde
    0.13
    -INF
    0.13
    anon
    0.13
    Act Density 0.125%

    No Known Activations