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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating reasons or causation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stě
    -0.82
     kormány
    -0.78
     vuotta
    -0.76
    jména
    -0.74
     gyerme
    -0.74
     társ
    -0.74
     obicei
    -0.73
     rând
    -0.73
     preocupação
    -0.72
     polícia
    -0.72
    POSITIVE LOGITS
     за
    0.91
    За
    0.90
     por
    0.88
    opor
    0.87
    por
    0.84
    Por
    0.82
    Για
    0.81
    orianCalendar
    0.81
    POR
    0.80
     Por
    0.79
    Act Density 0.036%

    No Known Activations