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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reviews or evaluations of artistic works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Butterfly
    -0.15
    heimer
    -0.15
    à¤¾à¤ł
    -0.14
    anke
    -0.14
     ãĤŃãĥ£
    -0.14
    .Companion
    -0.13
    è²Ŀ
    -0.13
    æŁ´
    -0.13
     decl
    -0.13
     womb
    -0.13
    POSITIVE LOGITS
     fly
    0.27
     flies
    0.27
     Fly
    0.23
    fly
    0.23
    flies
    0.22
    -fly
    0.21
    Fly
    0.19
     hover
    0.17
    uzz
    0.16
     Cul
    0.16
    Act Density 0.018%

    No Known Activations