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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or additions

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

    in addition to, beyond, besides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     başına
    -0.37
     bleus
    -0.37
     consecu
    -0.34
    going
    -0.33
    KommentareTeilen
    -0.33
    ことです
    -0.33
     ذهن
    -0.32
     because
    -0.32
     since
    -0.31
     imperf
    -0.30
    POSITIVE LOGITS
    verwijspagina
    0.75
     autorytatywna
    0.71
    enumii
    0.70
     intptr
    0.58
    ніципа
    0.56
    Oltre
    0.56
    Autoritní
    0.55
    rungsseite
    0.53
    enumi
    0.52
    ftant
    0.52
    Act Density 0.084%

    No Known Activations