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

    Neuronpedia

    INDEX
    Explanations

    mentions of unusual or unexpected ingredients in contexts unrelated to food

    oai_token-act-pair · gpt-3.5-turbo

    references to unconventional or unique materials and their contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.57
    �
    -0.56
     âĢİ
    -0.53
     ..........
    -0.48
     âĢº
    -0.46
    âĸł
    -0.45
     �
    -0.44
     abs
    -0.43
    tons
    -0.43
    -0.43
    POSITIVE LOGITS
    pload
    0.57
     guiActiveUn
    0.56
    ultimate
    0.53
    ãĤ´ãĥ³
    0.51
     Mechdragon
    0.50
    gyn
    0.50
    erker
    0.50
     condem
    0.49
     Hera
    0.49
     Annotations
    0.49
    Act Density 3.173%

    No Known Activations