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

    Neuronpedia

    INDEX
    Explanations

    terms related to inclusion in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĨĴ
    -1.94
    »¿
    -1.92
    Į
    -1.88
    ķ
    -1.79
    §
    -1.79
    Ŀ
    -1.78
    unnumbered
    -1.73
    Ļª
    -1.70
    ĵ
    -1.66
    ¸
    -1.65
    POSITIVE LOGITS
    imates
    1.91
    cript
    1.74
    aneous
    1.65
     appears
    1.58
    andidate
    1.53
    paired
    1.52
     limits
    1.52
    andidates
    1.51
    agraph
    1.51
    uer
    1.49
    Act Density 0.014%

    No Known Activations