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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to greetings and common expressions in a mix of languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.67
    دانشنامهٔ
    -0.61
    PerformLayout
    -0.60
    VersionUID
    -0.60
    GTCX
    -0.59
    舺
    -0.59
     queſta
    -0.59
     Paglinawan
    -0.56
    -0.56
    UnknownFieldSet
    -0.56
    POSITIVE LOGITS
    )))
    0.44
     stupidly
    0.41
    ")))
    0.37
     terribly
    0.37
     somewhere
    0.35
    ))
    0.35
    (((
    0.35
    ))).
    0.35
    ))))
    0.34
     Somehow
    0.34
    Act Density 0.067%

    No Known Activations