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

    Neuronpedia

    INDEX
    Explanations

    numerical values and identifiers related to data or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     calendriers
    -0.59
     مشين
    -0.55
     Poz
    -0.54
     विश्वसनीयता
    -0.53
    msgTypes
    -0.52
     onOptions
    -0.52
     balanceOf
    -0.52
     regia
    -0.50
    ctomy
    -0.50
    rups
    -0.50
    POSITIVE LOGITS
     propOrder
    0.79
    ientôt
    0.67
    cestry
    0.64
    ]-->
    0.60
    ウター
    0.60
    gapi
    0.59
    ThroughAttribute
    0.59
    IntoConstraints
    0.58
     MIB
    0.57
     préférable
    0.56
    Act Density 0.720%

    No Known Activations