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

    Neuronpedia

    INDEX
    Explanations

    key phrases that indicate conclusions or significant decisions being made

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +#+#
    -0.63
     consultato
    -0.47
    choly
    -0.45
    RLock
    -0.44
     &___
    -0.43
    Cursors
    -0.42
    split
    -0.41
    reat
    -0.40
    Tetapi
    -0.40
    parametrize
    -0.40
    POSITIVE LOGITS
     صوتيه
    0.69
    AutoScale
    0.62
    SBATCH
    0.61
    }],
    0.59
    LookAnd
    0.59
    ❮
    0.59
    ConstraintMaker
    0.58
    Personendaten
    0.57
    الحياه
    0.56
     setuptools
    0.56
    Act Density 0.185%

    No Known Activations