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

    Neuronpedia

    INDEX
    Explanations

    the word "though" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igo
    -0.17
     Ñģобой
    -0.16
    Ả
    -0.16
    ãģ¹ãģį
    -0.15
    cken
    -0.15
    à¹Ģลย
    -0.15
     either
    -0.14
    äºİæĺ¯
    -0.14
    ised
    -0.14
    ER
    -0.13
    POSITIVE LOGITS
    s
    0.35
    out
    0.25
    soever
    0.22
     they
    0.21
    forth
    0.21
    Ùĩ
    0.21
    OUT
    0.20
     shalt
    0.20
     not
    0.20
     there
    0.19
    Act Density 0.044%

    No Known Activations