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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the letter "j" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ж
    -0.59
     Ј
    -0.56
     EJ
    -0.56
     Já
    -0.53
     Jobs
    -0.53
     Jou
    -0.51
    IntoConstraints
    -0.51
    EJ
    -0.49
    Ж
    -0.49
    ZJ
    -0.48
    POSITIVE LOGITS
    j
    1.28
    je
    1.23
    jo
    1.18
    jen
    1.17
    ju
    1.15
     j
    1.13
    jes
    1.11
    jer
    1.08
    jk
    1.05
    jn
    1.05
    Act Density 1.360%

    No Known Activations