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

    Neuronpedia

    INDEX
    Explanations

    technical terminology and their implications in specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.75
     ſtate
    -0.68
     pleaſure
    -0.63
     تانيه
    -0.62
     juſ
    -0.62
    IntoConstraints
    -0.62
     Majefty
    -0.61
     ſche
    -0.60
     juſt
    -0.59
     uſed
    -0.58
    POSITIVE LOGITS
     nonetheless
    0.55
    igshid
    0.53
     nevertheless
    0.53
     trotzdem
    0.51
     dennoch
    0.48
    
    0.47
     EconPapers
    0.47
    Lähteet
    0.45
    الحياه
    0.45
    ]")]
    0.44
    Act Density 0.395%

    No Known Activations