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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions or step-by-step guides

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "there" and phrases indicating existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.65
    chuk
    -0.61
    aura
    -0.57
    {{
    -0.57
    Knight
    -0.56
    AMI
    -0.56
    è£
    -0.55
    sylv
    -0.55
    chnology
    -0.54
    Eth
    -0.54
    POSITIVE LOGITS
     ISI
    0.55
     ye
    0.52
    netflix
    0.50
    othe
    0.49
    bra
    0.49
    rius
    0.48
    )!
    0.47
     Palestinians
    0.47
     Andy
    0.47
     mods
    0.46
    Act Density 0.460%

    No Known Activations