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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to personal experiences and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asti
    -0.17
    aines
    -0.17
    acie
    -0.16
    ONO
    -0.15
    uti
    -0.15
    ipt
    -0.15
    ýt
    -0.14
    pom
    -0.14
    ivet
    -0.14
     BOTH
    -0.14
    POSITIVE LOGITS
     necessarily
    0.27
     immediately
    0.21
     completely
    0.19
     carte
    0.19
     solely
    0.19
     exclusively
    0.18
     absolutely
    0.18
     entirely
    0.18
     sole
    0.18
     totally
    0.17
    Act Density 0.344%

    No Known Activations