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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases that indicate relationships between ideas and comparisons

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

    followed by pronouns

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cyjne
    -0.53
    efel
    -0.52
     heller
    -0.52
    lehre
    -0.51
    orical
    -0.51
    ubblica
    -0.50
     abgerufen
    -0.50
    titut
    -0.50
    ulemon
    -0.49
     natomiast
    -0.49
    POSITIVE LOGITS
     يتيمه
    1.04
     admittedly
    0.89
    ConstraintMaker
    0.86
    WithMany
    0.84
     nahilalakip
    0.82
    middels
    0.79
    LookAnd
    0.75
    !—
    0.73
    verwijspagina
    0.73
     البته
    0.71
    Act Density 0.190%

    No Known Activations