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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons or distinctions

    oai_token-act-pair · gpt-3.5-turbo

    connections or comparisons between ideas or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =(
    -0.70
     ILCS
    -0.70
    !".
    -0.62
    zers
    -0.60
    ãĢį
    -0.60
    .ãĢį
    -0.59
    ((
    -0.58
    .–
    -0.57
    zona
    -0.56
    pointers
    -0.56
    POSITIVE LOGITS
    ILA
    0.62
    onential
    0.59
     understatement
    0.58
     elegance
    0.58
    arious
    0.55
    perfect
    0.53
     diligence
    0.53
    otic
    0.53
     Responsibility
    0.53
    isite
    0.52
    Act Density 0.387%

    No Known Activations