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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various activities undertaken or initiated by individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or quantities associated with measurement or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     describ
    -0.84
     neighb
    -0.83
     oun
    -0.76
     destro
    -0.71
     Mub
    -0.68
     prosec
    -0.66
     Blair
    -0.66
     Sin
    -0.66
     Hero
    -0.66
     Melvin
    -0.65
    POSITIVE LOGITS
    Advertisement
    1.22
    Advertisements
    1.21
    âĨij
    1.20
    RAW
    1.17
    Trivia
    1.17
    ©
    1.13
    Examples
    1.08
    References
    1.08
    Discussion
    1.07
    >>
    1.05
    Act Density 0.337%

    No Known Activations