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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional states or reactions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "I was" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iosyncr
    -0.73
    izable
    -0.67
    worthiness
    -0.66
    negie
    -0.66
     exploits
    -0.66
    士
    -0.65
    ð
    -0.64
    luence
    -0.64
    vernment
    -0.63
    èĢħ
    -0.63
    POSITIVE LOGITS
     amazed
    1.17
     terrified
    1.16
     afraid
    1.14
     ecstatic
    1.10
     horrified
    1.08
     scared
    1.08
     glad
    1.07
     shocked
    1.07
     devastated
    1.05
     tempted
    1.05
    Act Density 0.169%

    No Known Activations