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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning legal and bureaucratic terms

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to significant societal issues or threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sacrific
    -0.82
     ende
    -0.80
     reflection
    -0.76
     obser
    -0.76
     readable
    -0.74
     unconscious
    -0.74
     floppy
    -0.73
     outline
    -0.73
     canv
    -0.72
     confir
    -0.71
    POSITIVE LOGITS
    ¯
    1.16
    âĢł
    0.95
    ¶
    0.87
    ï¸ı
    0.85
    âģ
    0.85
    °
    0.85
    ï¸
    0.84
    §
    0.84
    SHIP
    0.84
    ¨
    0.83
    Act Density 0.221%

    No Known Activations