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

    Neuronpedia

    INDEX
    Explanations

    beginning phrases or formatting indicators in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.68
    AnchorStyles
    -0.67
     EdgeInsets
    -0.66
    fromnode
    -0.66
    +#+#
    -0.63
    󠁢
    -0.63
    Obrázky
    -0.61
    Tazama
    -0.60
    Kaieteur
    -0.58
    UpInside
    -0.57
    POSITIVE LOGITS
     Савезне
    0.63
     itſelf
    0.57
     Biôgrafia
    0.54
     Jefus
    0.53
    WithIOException
    0.52
     myſelf
    0.52
    ThroughAttribute
    0.52
     resourceCulture
    0.51
     ſta
    0.50
     himſelf
    0.49
    Act Density 0.087%

    No Known Activations