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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating simplicity or ease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    that followed by adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    JsonNode
    -0.47
    PSS
    -0.42
    存于互联网档案馆
    -0.42
    Архівовано
    -0.41
    iNdEx
    -0.40
    MCS
    -0.40
    ActionMode
    -0.40
    SCS
    -0.39
    SequentialGroup
    -0.39
    -------
    -0.39
    POSITIVE LOGITS
     VERY
    0.50
    @@@@@@@@
    0.49
    そんなに
    0.48
    chita
    0.47
     dissimilar
    0.47
     kinda
    0.46
     Terrell
    0.46
     very
    0.46
     Moff
    0.45
     MUCH
    0.45
    Act Density 0.008%

    No Known Activations