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

    Neuronpedia

    INDEX
    Explanations

    instances of words related to treating and mistreatment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concepts of creation and treatment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endorsements
    -0.66
     summ
    -0.61
     analytical
    -0.60
     tactical
    -0.60
     Russell
    -0.59
     Economy
    -0.59
     Luck
    -0.59
     fraction
    -0.56
     shorthand
    -0.55
     sem
    -0.55
    POSITIVE LOGITS
    reating
    3.77
    reated
    3.73
    reat
    2.82
    reatment
    2.79
    aliation
    1.28
    ruly
    1.11
    rait
    1.08
    onew
    1.06
    render
    1.02
    ricks
    1.01
    Act Density 0.032%

    No Known Activations