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

    Neuronpedia

    INDEX
    Explanations

    references to educational or academic classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usp
    -1.71
    ably
    -1.71
    cil
    -1.66
    imize
    -1.64
    ariat
    -1.63
    iator
    -1.63
    iate
    -1.48
    ener
    -1.44
    ue
    -1.44
    uate
    -1.43
    POSITIVE LOGITS
    "];
    2.06
    '];
    1.66
    omitempty
    1.59
    vasive
    1.57
     laws
    1.45
    omorphisms
    1.45
    ']);
    1.43
    /~
    1.37
    laws
    1.36
     ourselves
    1.35
    Act Density 0.225%

    No Known Activations