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

    Neuronpedia

    INDEX
    Explanations

    words related to conflict and struggle

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas used in a variety of contexts within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Horses
    -0.74
    EStream
    -0.70
    obia
    -0.67
    Į
    -0.66
    ORS
    -0.65
     proble
    -0.65
    OME
    -0.65
    swick
    -0.64
    Players
    -0.64
    ESE
    -0.63
    POSITIVE LOGITS
     albeit
    1.16
     um
    0.79
    albeit
    0.75
     uh
    0.71
     undisclosed
    0.71
     localized
    0.70
     vocal
    0.69
     contrasting
    0.68
     inclusive
    0.67
     huh
    0.67
    Act Density 0.244%

    No Known Activations