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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to regulatory actions and contexts in various domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    207
    -0.16
    ople
    -0.15
    ennes
    -0.15
    arty
    -0.14
    opus
    -0.14
     Butter
    -0.14
     Giov
    -0.14
    aza
    -0.14
    ä¾į
    -0.14
     reve
    -0.14
    POSITIVE LOGITS
    Ú¯ÙĦ
    0.16
     pet
    0.15
    -wing
    0.15
    osate
    0.15
     blood
    0.14
    ona
    0.14
    blo
    0.14
    bv
    0.14
    CLEAR
    0.14
     circle
    0.14
    Act Density 0.026%

    No Known Activations