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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic or technical discussions and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ordinal numbers

    np_acts-logits-general · gemini-2.0-flash

    third or ordinal numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Exacts
    -0.70
    PostInfinity
    -0.56
    DeleteBehavior
    -0.53
    idenav
    -0.53
    ++];
    -0.51
    UrlResolution
    -0.47
    umoj
    -0.47
    Specifically
    -0.47
     TimeUnit
    -0.47
     kanyang
    -0.47
    POSITIVE LOGITS
     third
    1.41
    third
    1.29
     dritte
    1.08
    Third
    1.08
     fourth
    1.08
     terceira
    1.00
     terceiro
    1.00
     troisième
    1.00
     THIRD
    0.98
    第三
    0.98
    Act Density 0.714%

    No Known Activations