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

    Neuronpedia

    INDEX
    Explanations

    academic affiliations and conference presentations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.87
    NUMX
    -0.85
    )':
    -0.79
     XNUMX
    -0.73
    !")
    -0.70
    {})
    -0.69
    CppMethod
    -0.69
    `),
    -0.68
    ...')
    -0.68
    ...")
    -0.67
    POSITIVE LOGITS
    ,
    1.49
     –
    0.61
     -
    0.57
    ،
    0.57
     ,
    0.53
    ;
    0.46
     /
    0.44
    ,\\
    0.44
    ，
    0.44
    *,
    0.43
    Act Density 0.662%

    No Known Activations