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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contextual significance

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

    Punctuation followed by a conjunction

    np_acts-logits-general · gemini-2.0-flash

    statement continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jedoch
    -0.82
    Whilst
    -0.81
     Дан
    -0.80
     Firstly
    -0.79
    Firstly
    -0.79
     Whilst
    -0.79
     Somit
    -0.79
     somit
    -0.77
    の為
    -0.76
     therefor
    -0.76
    POSITIVE LOGITS
     Ditto
    0.85
     And
    0.81
     (“
    0.79
     freilich
    0.76
     Indeed
    0.74
     doubtless
    0.71
     Worse
    0.70
    Indeed
    0.69
    ppure
    0.69
     disambiguazione
    0.69
    Act Density 0.325%

    No Known Activations