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

    Neuronpedia

    INDEX
    Explanations

    phrases involving conditional statements or technical explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.03
     purpoſe
    -0.86
     pleaſure
    -0.84
    OGND
    -0.79
     invid
    -0.78
     Platon
    -0.78
     ་་
    -0.72
     Houſe
    -0.71
     Anſ
    -0.70
     leaſt
    -0.69
    POSITIVE LOGITS
     Se
    0.84
     se
    0.83
     haberse
    0.82
     sa
    0.75
     להת
    0.72
    ➢
    0.71
    amse
    0.70
    )):
    0.68
    się
    0.68
    Se
    0.68
    Act Density 0.017%

    No Known Activations