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

    Neuronpedia

    INDEX
    Explanations

    phrases that express high quality or strong emotions

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

    Adjectives after intensifiers

    np_acts-logits-general · gemini-2.0-flash

    intensifier followed by positive descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.68
     ModelExpression
    -0.65
    ьаж
    -0.65
    }));
    -0.63
    ]),
    -0.62
    MessageOf
    -0.59
    TypedDataSet
    -0.57
    ']],
    -0.56
    ']);
    -0.56
     Photocase
    -0.56
    POSITIVE LOGITS
     inviting
    0.73
     engaging
    0.67
     rewarding
    0.58
     ویکی‌پدیای
    0.58
     satisfying
    0.56
     appealing
    0.55
     striking
    0.53
     fulfilling
    0.51
     dynamic
    0.51
    thyst
    0.51
    Act Density 0.163%

    No Known Activations