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

    Neuronpedia

    INDEX
    Explanations

    keywords related to evaluation and comparison

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

    preceding a contrast or alternative

    np_acts-logits-general · gemini-2.0-flash

    concession or contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oznam
    -0.40
    الحياه
    -0.39
    ykite
    -0.39
    erschiedene
    -0.38
    Jereo
    -0.38
    ighting
    -0.36
    tiéndose
    -0.36
    Referințe
    -0.36
     Füßen
    -0.36
    :✨
    -0.36
    POSITIVE LOGITS
     but
    0.70
     nhưng
    0.57
    withIdentifier
    0.51
     mutta
    0.47
    りますが
    0.46
     mais
    0.46
     pero
    0.45
     But
    0.45
     nice
    0.44
    けど
    0.44
    Act Density 0.529%

    No Known Activations