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

    Neuronpedia

    INDEX
    Explanations

    instances of statements and opinions

    oai_token-act-pair · gpt-3.5-turbo

    affirmations or positive sentiments about collective efforts or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.76
    ãĥ¥
    -0.73
     Miracle
    -0.72
     Gadget
    -0.69
    ĸļ
    -0.68
    Mech
    -0.68
    quick
    -0.66
     Maze
    -0.66
     maze
    -0.66
     miraculous
    -0.65
    POSITIVE LOGITS
     endorse
    1.45
     voted
    1.40
     oppose
    1.30
     opposes
    1.29
     vote
    1.29
     opposed
    1.27
     disagree
    1.25
     sympath
    1.24
     endorsed
    1.24
     endorsing
    1.19
    Act Density 0.672%

    No Known Activations