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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and special characters with specific patterns

    oai_token-act-pair · gpt-3.5-turbo

    numerical or categorical data related to institutions or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utz
    -0.76
    unk
    -0.76
    frey
    -0.74
    unks
    -0.69
    una
    -0.69
    UMP
    -0.68
    ohm
    -0.67
    ulas
    -0.67
     Ogre
    -0.67
    lessness
    -0.64
    POSITIVE LOGITS
    C
    1.22
    CI
    1.18
    CS
    1.12
    CC
    1.11
    CB
    1.10
    cs
    1.09
    cp
    1.08
    CP
    1.06
    ci
    1.06
    c
    1.05
    Act Density 0.669%

    No Known Activations