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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific cases or examples being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    in case of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    intenant
    -0.49
    mær
    -0.47
     juſ
    -0.46
    stree
    -0.45
    tiérrez
    -0.45
     humanidade
    -0.43
     Connectez
    -0.43
     dieux
    -0.42
    pography
    -0.42
     ouvriers
    -0.42
    POSITIVE LOGITS
     cases
    0.81
     case
    0.76
    Personendaten
    0.72
     caso
    0.71
    Caso
    0.68
     случае
    0.65
     przypadku
    0.65
     Caso
    0.63
     Case
    0.63
    ณี
    0.63
    Act Density 0.021%

    No Known Activations