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

    Neuronpedia

    INDEX
    Explanations

    code-related assertions and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awe
    -0.15
     Fancy
    -0.15
    át
    -0.14
     Bot
    -0.14
     cad
    -0.14
    .IsNull
    -0.13
     dus
    -0.13
     privileged
    -0.13
    ASM
    -0.13
    tin
    -0.13
    POSITIVE LOGITS
    ayah
    0.15
    ucene
    0.15
    arna
    0.15
    atego
    0.14
    ừng
    0.14
    akat
    0.14
    ustum
    0.14
     Ziel
    0.14
     EXPECT
    0.14
    gua
    0.14
    Act Density 0.048%

    No Known Activations