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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships between entities and concepts within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     genders
    -0.24
     Gary
    -0.22
     Gamma
    -0.21
     Gender
    -0.20
     gamma
    -0.20
    .gender
    -0.20
     gases
    -0.20
    .gamma
    -0.19
    Gary
    -0.19
    _google
    -0.19
    POSITIVE LOGITS
     bad
    0.22
    .Setter
    0.21
    æĤª
    0.18
    bad
    0.18
     n
    0.17
    erne
    0.17
     Bad
    0.17
     Silver
    0.17
     silver
    0.17
    @Setter
    0.16
    Act Density 0.129%

    No Known Activations