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

    Neuronpedia

    INDEX
    Explanations

    comparative and contrasting phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yw
    -0.36
     jed
    -0.36
     kapp
    -0.36
     Jed
    -0.34
    SA
    -0.33
     uren
    -0.33
    優
    -0.33
    衡
    -0.33
     اي
    -0.33
    ই
    -0.33
    POSITIVE LOGITS
    ConstraintMaker
    0.91
    RegistryLite
    0.83
    ScopeManager
    0.82
     CreateTagHelper
    0.82
    UnknownFields
    0.81
    elemField
    0.80
    帖最后由
    0.79
     lenker
    0.78
    principalColumn
    0.77
    OGND
    0.75
    Act Density 0.508%

    No Known Activations