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

    Neuronpedia

    INDEX
    Explanations

    numerical concepts and the occurrence of likelihood in probabilistic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     competitive
    -0.15
     fra
    -0.14
    avan
    -0.14
    å¸
    -0.14
    аÑĦ
    -0.14
     Bart
    -0.13
    åı
    -0.13
    iffin
    -0.13
    entes
    -0.13
    igaret
    -0.13
    POSITIVE LOGITS
     balls
    0.19
    .intellij
    0.18
     Correct
    0.17
     drawn
    0.16
    èĥĨ
    0.16
    éŃ¯
    0.15
     Balls
    0.15
    hoff
    0.15
    correct
    0.15
    Correct
    0.15
    Act Density 0.000%

    No Known Activations