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

    Neuronpedia

    INDEX
    Explanations

    comparative expressions and phrases indicating similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roe
    -0.17
     EITHER
    -0.15
    pedo
    -0.15
    ses
    -0.15
    onical
    -0.15
    asca
    -0.15
    rou
    -0.15
    каÑģ
    -0.14
    ãģķãĤī
    -0.14
     sice
    -0.14
    POSITIVE LOGITS
    -minded
    0.37
     minded
    0.31
     any
    0.29
    WISE
    0.28
     clock
    0.28
    able
    0.28
     unto
    0.28
     usual
    0.23
     always
    0.23
    ability
    0.23
    Act Density 0.098%

    No Known Activations