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

    Neuronpedia

    INDEX
    Explanations

    words or characters associated with mathematical or technical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lez
    -0.17
    arton
    -0.16
    ethnic
    -0.15
    opa
    -0.14
    368
    -0.14
    æ°ijæĹı
    -0.14
    drž
    -0.14
    _nullable
    -0.14
    atives
    -0.13
    romatic
    -0.13
    POSITIVE LOGITS
     Equal
    0.25
     Equality
    0.21
     Money
    0.20
    Equal
    0.20
     abuse
    0.19
     equal
    0.18
     Abuse
    0.18
     Dest
    0.17
     money
    0.17
     EQUAL
    0.17
    Act Density 0.005%

    No Known Activations