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

    Neuronpedia

    INDEX
    Explanations

    concepts related to statistical models and their relationships

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    `;
    -0.52
    Warmly
    -0.49
    `,
    -0.49
    '),
    -0.47
    ]=$
    -0.46
    newName
    -0.46
    nál
    -0.45
     shuffling
    -0.45
    ;">
    -0.44
    ]}>
    -0.44
    POSITIVE LOGITS
     الحره
    0.81
    AndEndTag
    0.74
    DockStyle
    0.73
     للاسماء
    0.73
     мәкал
    0.72
    intios
    0.72
     صوتيه
    0.71
    BeginContext
    0.69
     autorytatywna
    0.68
    Personensuche
    0.66
    Act Density 0.138%

    No Known Activations