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

    Neuronpedia

    INDEX
    Explanations

    informal expressions and conversational cues in language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mourut
    -0.47
    Rhestr
    -0.43
     AttributeSet
    -0.43
    DockStyle
    -0.42
    escens
    -0.40
    Solución
    -0.40
    XmlAccessType
    -0.37
    çoivent
    -0.36
     Administrativna
    -0.36
    脚注の使い方
    -0.35
    POSITIVE LOGITS
     don
    2.22
     Don
    1.73
    Don
    1.70
    don
    1.70
     DON
    1.64
     jangan
    1.55
     dont
    1.50
     DONT
    1.45
     Jangan
    1.44
    DON
    1.43
    Act Density 0.553%

    No Known Activations