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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to self-identity and self-expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¥
    -0.15
    ãĥ£
    -0.15
    agner
    -0.15
    ainment
    -0.14
     Jensen
    -0.14
    पन
    -0.14
    .bp
    -0.14
    .LookAndFeel
    -0.14
     teng
    -0.14
    usp
    -0.14
    POSITIVE LOGITS
    /self
    0.26
    (Self
    0.20
     self
    0.19
    ridge
    0.18
    lessly
    0.18
    änd
    0.18
     Self
    0.17
    =self
    0.17
    (self
    0.17
    same
    0.17
    Act Density 0.029%

    No Known Activations