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

    Neuronpedia

    INDEX
    Explanations

    terms related to parameters and metrics in experiments or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æīķ
    -0.15
     Beverly
    -0.15
    eko
    -0.15
    strand
    -0.14
    .cam
    -0.14
    erta
    -0.14
    mailto
    -0.14
    è¾¼
    -0.14
    amin
    -0.14
    usto
    -0.14
    POSITIVE LOGITS
    .MixedReality
    0.16
    rophe
    0.16
     consc
    0.15
    erif
    0.15
    oons
    0.15
    erb
    0.14
    anoia
    0.14
    embro
    0.14
     Morg
    0.14
    oningen
    0.14
    Act Density 0.009%

    No Known Activations