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

    Neuronpedia

    INDEX
    Explanations

    contractions or possessive determiners

    oai_token-act-pair · gpt-3.5-turbo

    apostrophes, particularly their usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eclipse
    -0.66
    conservancy
    -0.65
    ynski
    -0.62
     sidel
    -0.62
     contrast
    -0.60
     transpl
    -0.59
    isphere
    -0.58
     Izan
    -0.57
     cycle
    -0.56
     prin
    -0.55
    POSITIVE LOGITS
    Mech
    0.80
    Brien
    0.79
    alon
    0.79
    MIC
    0.78
    nai
    0.77
    eworks
    0.76
    Donnell
    0.75
    nos
    0.75
    atri
    0.75
    ',
    0.74
    Act Density 0.055%

    No Known Activations