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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrast or qualifiers that describe attributes

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

    contrast or addition

    np_acts-logits-general · gemini-2.0-flash

    but, yet, also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sogar
    -0.56
    bedo
    -0.55
     semej
    -0.53
    Storia
    -0.49
    vábbi
    -0.48
    jsoup
    -0.48
    Incluso
    -0.47
     dokonce
    -0.47
     semejante
    -0.47
     például
    -0.46
    POSITIVE LOGITS
     also
    1.41
    Also
    1.12
    also
    1.12
     alſo
    1.10
     Also
    1.10
    却又
    1.05
    但也
    1.03
    又能
    1.02
     jednocześnie
    1.00
     ALSO
    0.99
    Act Density 0.242%

    No Known Activations