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

    Neuronpedia

    INDEX
    Explanations

    the word "Being" followed by a descriptive phrase

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Being" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rez
    -0.75
    ummy
    -0.74
    ="#
    -0.73
    ett
    -0.71
    ummies
    -0.70
    OUP
    -0.69
    és
    -0.68
    ère
    -0.66
    dress
    -0.63
    ombat
    -0.63
    POSITIVE LOGITS
    ©¶æ
    0.80
     deprived
    0.79
    etheless
    0.74
     reluct
    0.71
     immersed
    0.70
     intimidated
    0.70
     exhausted
    0.69
     unable
    0.68
     minded
    0.68
     able
    0.68
    Act Density 0.065%

    No Known Activations