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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest a desire for information and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.79
     habet
    -0.73
     autorytatywna
    -0.70
    ArgsConstructor
    -0.70
    XmlAccessType
    -0.66
    orteur
    -0.66
    ̈́
    -0.65
     Hauteur
    -0.63
     habis
    -0.62
    odeon
    -0.61
    POSITIVE LOGITS
     برانيه
    0.63
    :)
    0.53
    Clik
    0.51
    utica
    0.48
     learn
    0.47
     ask
    0.46
    сля
    0.45
    ddagger
    0.45
    ↵↵
    0.45
    overline
    0.45
    Act Density 0.116%

    No Known Activations