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

    Neuronpedia

    INDEX
    Explanations

    marks of procedural or academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.68
     Efq
    -0.68
     spared
    -0.67
    ProgressHUD
    -0.66
     متعلقه
    -0.65
     Pyrr
    -0.63
     Shakspeare
    -0.61
    itudinal
    -0.59
     Doubleday
    -0.59
     involunt
    -0.58
    POSITIVE LOGITS
     worry
    0.54
     Worry
    0.51
     venuto
    0.49
    mitteilung
    0.47
     sık
    0.46
    紛
    0.46
     issues
    0.45
    怎么办
    0.44
     You
    0.43
    getattr
    0.43
    Act Density 0.552%

    No Known Activations