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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating relative levels of quality or effectiveness

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

    "or" followed by comparative words

    np_acts-logits-general · gemini-2.0-flash

    comparisons with 'or'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.54
    Equal
    -0.51
    Stay
    -0.50
    Adult
    -0.49
    GOTREF
    -0.48
    isInitialized
    -0.47
    mah
    -0.47
     equalization
    -0.47
     Stay
    -0.47
    qua
    -0.47
    POSITIVE LOGITS
     Audiodateien
    0.67
     slightly
    0.65
    XtraEditors
    0.65
     noqa
    0.65
    slightly
    0.64
    Slightly
    0.62
     kì
    0.60
     Slightly
    0.60
     GenerationType
    0.60
    GeneratedCode
    0.60
    Act Density 0.454%

    No Known Activations