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

    Neuronpedia

    INDEX
    Explanations

    comparisons between different approaches or choices

    oai_token-act-pair · gpt-3.5-turbo

    comparisons emphasizing a preference or emphasis on alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amba
    -0.79
     DRAG
    -0.71
    adium
    -0.69
    eria
    -0.67
    eland
    -0.66
    clud
    -0.66
    elaide
    -0.65
    iculture
    -0.65
    iola
    -0.65
    pet
    -0.63
    POSITIVE LOGITS
     than
    0.78
     unimagin
    0.70
     trivial
    0.68
     preferring
    0.67
    than
    0.65
     Ide
    0.61
     envis
    0.61
     inconvenient
    0.61
     resembling
    0.60
     Leh
    0.60
    Act Density 0.016%

    No Known Activations