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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Exteriores
    -0.59
    BeginContext
    -0.57
    Gön
    -0.54
     normaux
    -0.53
     creativa
    -0.52
    CppCodeGen
    -0.51
     paisagem
    -0.51
     nécessité
    -0.50
     creativos
    -0.50
    ksessa
    -0.49
    POSITIVE LOGITS
     about
    0.81
     sobre
    0.78
     tentang
    0.75
     关于
    0.74
    关于
    0.74
     Sobre
    0.73
    關於
    0.72
     בנושא
    0.72
     how
    0.72
     về
    0.71
    Act Density 0.199%

    No Known Activations