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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that signal the end of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.68
    ỡng
    -0.59
    ſicht
    -0.57
    ellees
    -0.56
     Rol
    -0.55
    期刊论文
    -0.55
    burgers
    -0.54
    󠁬
    -0.54
     propOrder
    -0.54
    extAlignment
    -0.54
    POSITIVE LOGITS
    .*")]
    0.46
    ↵↵
    0.44
    .”
    0.43
     Enough
    0.37
     enough
    0.35
    Enough
    0.35
    Though
    0.34
     estrena
    0.34
     Maintenant
    0.34
     suficientes
    0.34
    Act Density 0.055%

    No Known Activations