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

    Neuronpedia

    INDEX
    Explanations

    negative and critical phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Address
    -0.75
     address
    -0.74
     Division
    -0.74
     margin
    -0.71
     rotor
    -0.71
     avenue
    -0.71
     entry
    -0.70
     Tier
    -0.69
     Union
    -0.69
     ratification
    -0.69
    POSITIVE LOGITS
    your
    1.43
    same
    1.37
    every
    1.36
    shit
    1.32
    everything
    1.32
    another
    1.29
    enough
    1.27
    the
    1.27
    anything
    1.26
    nature
    1.25
    Act Density 0.097%

    No Known Activations