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

    Neuronpedia

    INDEX
    Explanations

    words related to beliefs and trusting in something or someone

    oai_token-act-pair · gpt-3.5-turbo

    expressions that convey belief or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Thumbnail
    -0.85
     sidel
    -0.68
    udo
    -0.67
    ateral
    -0.64
    yna
    -0.64
    levard
    -0.63
    ington
    -0.63
     reminder
    -0.63
    thumbnails
    -0.62
    ynski
    -0.62
    POSITIVE LOGITS
     paranormal
    0.71
     sincerity
    0.71
     supernatural
    0.71
     infall
    0.65
     independence
    0.63
     innate
    0.62
     someday
    0.62
     integrity
    0.62
     innocence
    0.61
     Messiah
    0.61
    Act Density 0.148%

    No Known Activations