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

    Neuronpedia

    INDEX
    Explanations

    phrases related to choices and preferences in visual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imbus
    -0.19
    obia
    -0.17
    å½
    -0.16
    igers
    -0.15
    ¶Į
    -0.15
    ìĽĥ
    -0.15
    亡
    -0.15
    orra
    -0.15
    Detach
    -0.15
    ebi
    -0.15
    POSITIVE LOGITS
    jec
    0.17
     conven
    0.16
     Burning
    0.15
    rosse
    0.14
    tte
    0.14
     cou
    0.14
    athe
    0.14
     pal
    0.14
     fun
    0.14
    igin
    0.14
    Act Density 0.020%

    No Known Activations