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

    Neuronpedia

    INDEX
    Explanations

    references to selection and suitability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mit
    -0.14
    illard
    -0.13
     ward
    -0.13
    iv
    -0.13
     Worth
    -0.13
    imar
    -0.13
     lieu
    -0.13
     cour
    -0.13
     NodeType
    -0.13
    .jav
    -0.12
    POSITIVE LOGITS
     fits
    0.61
     suits
    0.60
     fit
    0.60
    fit
    0.56
     suit
    0.52
    Fit
    0.52
     Fits
    0.52
    fits
    0.50
     fitting
    0.50
     Fit
    0.49
    Act Density 0.294%

    No Known Activations