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

    Neuronpedia

    INDEX
    Explanations

    adjectives expressing strong opinions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives indicating positive or negative evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    steps
    -0.84
    Americans
    -0.79
    Os
    -0.79
    ipples
    -0.78
    events
    -0.75
    ques
    -0.75
     Machines
    -0.74
    attacks
    -0.73
    objects
    -0.73
    Nazis
    -0.73
    POSITIVE LOGITS
     reputation
    1.42
     knack
    1.41
     tendency
    1.30
     penchant
    1.29
     grasp
    1.24
     arsenal
    1.16
     repertoire
    1.14
     relationship
    1.12
     propensity
    1.12
     habit
    1.11
    Act Density 0.163%

    No Known Activations