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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uniqueness or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.65
    CopyWith
    -0.61
     poffible
    -0.58
     calendriers
    -0.57
    urfs
    -0.50
    EndGlobalSection
    -0.49
    ?></
    -0.49
    gebob
    -0.49
     bygga
    -0.49
    skraft
    -0.48
    POSITIVE LOGITS
     otomatig
    0.56
    onOptions
    0.56
    gav
    0.55
    исленность
    0.55
    Mur
    0.53
    жели
    0.52
    ErrUnexpectedEOF
    0.51
     []:
    0.50
     Cover
    0.50
    chauer
    0.50
    Act Density 0.339%

    No Known Activations