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

    Neuronpedia

    INDEX
    Explanations

    the representation of mathematical operations or symbols

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Kessler
    -0.84
     lenker
    -0.77
     Mende
    -0.77
    Geplaatst
    -0.76
     Foire
    -0.76
     fumar
    -0.75
     quæ
    -0.71
     Coz
    -0.69
     BMS
    -0.68
     informée
    -0.68
    POSITIVE LOGITS
    ⁢
    1.29
    ⁡
    1.02
     +
    0.79
    ]--;
    0.77
     kapcs
    0.70
    ")));
    0.65
    ⁣
    0.65
     \
    0.65
    Alg
    0.60
    _
    0.59
    Act Density 0.004%

    No Known Activations