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

    Neuronpedia

    INDEX
    Explanations

    hyphens and dashes in textual contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.91
     Infórmanos
    -0.88
    ing
    -0.83
    ❤️❤️
    -0.81
    liesslich
    -0.80
    "]
    -0.78
    Kaya
    -0.78
    ⬇️
    -0.76
    ^)
    -0.76
     mall
    -0.75
    POSITIVE LOGITS
    –
    1.02
     `/
    1.01
    =`
    0.98
     Â
    0.94
    ########.
    0.93
     المُ
    0.90
    UIControlState
    0.89
     `
    0.89
    .–
    0.85
     مُ
    0.84
    Act Density 0.154%

    No Known Activations