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

    Neuronpedia

    INDEX
    Explanations

    words related to decrease or downgrade

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'downplaying' or minimizing significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andum
    -0.70
    acca
    -0.66
    ¶ħ
    -0.63
    ë
    -0.60
    OST
    -0.60
    inen
    -0.60
     Kad
    -0.58
    aneous
    -0.58
    arians
    -0.57
    aceous
    -0.57
    POSITIVE LOGITS
    graded
    1.40
    grading
    1.37
    LOAD
    1.30
    played
    1.28
    sized
    1.24
    grades
    1.18
    playing
    1.18
    stairs
    1.15
    pour
    1.14
    hill
    1.12
    Act Density 0.046%

    No Known Activations