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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ability or potential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.44
     gynhyrchwyd
    -0.42
    <?
    -0.40
     &___
    -0.40
     beginnetje
    -0.38
     rejected
    -0.36
     initState
    -0.36
    Espèce
    -0.36
    XmlEnum
    -0.35
    hdys
    -0.35
    POSITIVE LOGITS
     can
    2.80
    Can
    1.91
     Can
    1.88
     können
    1.80
    可以
    1.80
    can
    1.80
     pouvez
    1.74
     можно
    1.68
     kann
    1.66
     pouvons
    1.63
    Act Density 0.243%

    No Known Activations