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

    Neuronpedia

    INDEX
    Explanations

    terms related to a specific subject or entity in a context resembling a discussion or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.89
     Jefus
    -0.89
     houſe
    -0.83
     pleaſure
    -0.82
     Houſe
    -0.81
     Monfieur
    -0.79
    WebElementEntity
    -0.78
    andangan
    -0.77
     reaſon
    -0.77
    RetentionPolicy
    -0.77
    POSITIVE LOGITS
     sa
    0.90
     coat
    0.76
    shout
    0.67
     ang
    0.65
     Ang
    0.60
     Sa
    0.60
     Coat
    0.57
    Viral
    0.56
    viral
    0.56
     Viral
    0.54
    Act Density 0.075%

    No Known Activations