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

    Neuronpedia

    INDEX
    Explanations

    words related to selection and evaluation of options or features

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

    reason for selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kollu
    -0.52
     wireType
    -0.45
     jornada
    -0.45
     betweenstory
    -0.44
     spôso
    -0.42
     either
    -0.42
    balleur
    -0.42
     caminhada
    -0.40
     direção
    -0.40
    yní
    -0.40
    POSITIVE LOGITS
    因为它
    0.48
    是因为
    0.41
    ьаж
    0.41
     потому
    0.40
     Chwiliwch
    0.40
    saraba
    0.39
     because
    0.38
    DebuggerNonUser
    0.37
    because
    0.36
    tinyos
    0.36
    Act Density 0.043%

    No Known Activations