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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the emergence or rise of various trends or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aji
    -0.16
    TERS
    -0.14
    misc
    -0.14
    γμα
    -0.14
    NullOr
    -0.14
    .Imp
    -0.14
    uters
    -0.14
    ampo
    -0.14
     Tub
    -0.14
    naÄį
    -0.14
    POSITIVE LOGITS
    fad
    0.17
    $MESS
    0.16
    igos
    0.15
     new
    0.15
     Civilization
    0.15
    ernet
    0.15
    $__
    0.15
    ÏĥÏĦη
    0.14
    ÑĤен
    0.14
    iales
    0.14
    Act Density 0.075%

    No Known Activations