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

    Neuronpedia

    INDEX
    Explanations

    specific phrases emphasizing limitations or exclusivity in contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <=",
    -0.68
     semplicemente
    -0.67
    astéroïdes
    -0.66
    Geplaatst
    -0.65
    XMLSchema
    -0.63
    tvguidetime
    -0.63
    aarrggbb
    -0.62
     CreateTagHelper
    -0.62
     estekak
    -0.61
     StatelessWidget
    -0.60
    POSITIVE LOGITS
     remaining
    1.02
    remaining
    0.89
     Remaining
    0.78
    Remaining
    0.78
     possible
    0.76
     really
    0.74
     ever
    0.74
     downside
    0.70
     thing
    0.69
     imaginable
    0.68
    Act Density 0.151%

    No Known Activations