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

    Neuronpedia

    INDEX
    Explanations

    sentences that express conjecture or uncertainty

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -1.05
     kasarigan
    -0.95
     estekak
    -0.90
     ProtoMessage
    -0.85
    WireFormatLite
    -0.81
    aarrggbb
    -0.80
    chiali
    -0.79
    SuppressLint
    -0.78
    Geplaatst
    -0.78
    protoimpl
    -0.78
    POSITIVE LOGITS
     chercher
    0.63
    endphp
    0.60
     interessiert
    0.58
     szint
    0.55
     Tamb
    0.55
     mendes
    0.55
    geschlossen
    0.54
     Semp
    0.54
     Воз
    0.53
    tetur
    0.53
    Act Density 0.015%

    No Known Activations