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

    Neuronpedia

    INDEX
    Explanations

    the word "though" as it appears in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ised
    -0.16
    nt
    -0.16
    ct
    -0.15
    ULONG
    -0.15
    igo
    -0.15
    ãģĻãĤĭãģ¨
    -0.14
    aris
    -0.14
    CT
    -0.14
    riad
    -0.14
    ifact
    -0.14
    POSITIVE LOGITS
    ritz
    0.21
    s
    0.19
    odor
    0.18
    soever
    0.17
    azard
    0.16
    fully
    0.15
    lessly
    0.15
    ãģĬãĤĬ
    0.15
     Nhĩ
    0.15
     æ¬
    0.15
    Act Density 0.022%

    No Known Activations