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

    Neuronpedia

    INDEX
    Explanations

    words related to a significant change or increase

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant changes or criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Loaded
    -0.84
     Podcast
    -0.68
    Plex
    -0.66
    Fit
    -0.64
     Fun
    -0.61
    ios
    -0.59
     Olymp
    -0.59
     idols
    -0.59
     cloning
    -0.58
     NXT
    -0.58
    POSITIVE LOGITS
     sharply
    3.39
     harshly
    1.81
     markedly
    1.54
     abruptly
    1.52
     strongly
    1.43
     fiercely
    1.42
     forcefully
    1.29
     steadily
    1.27
     bitterly
    1.25
     dramatically
    1.23
    Act Density 0.016%

    No Known Activations