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

    Neuronpedia

    INDEX
    Explanations

    patterns related to structured data or formatting, such as statistical parameters or code syntax

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    <eos>
    -0.59
    </em>
    -0.52
    </strong>
    -0.51
     […]
    -0.48
     eccell
    -0.48
     gynhyrchwyd
    -0.43
     recruiting
    -0.43
    Diweddarwch
    -0.43
    RepeatedField
    -0.42
     ak
    -0.42
    POSITIVE LOGITS
    AutoScaleMode
    0.75
    ^(@)
    0.68
     myſelf
    0.66
    ſelves
    0.65
    tagHelperRunner
    0.63
     שוליים
    0.63
     itſelf
    0.63
     bershka
    0.61
     utafitiHapana
    0.60
    Diwedd
    0.59
    Act Density 0.500%

    No Known Activations