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

    Neuronpedia

    INDEX
    Explanations

    language related to probabilities and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asca
    -0.18
    ìŀij
    -0.16
    elli
    -0.15
    ulary
    -0.14
    ndl
    -0.14
    èĮ¨
    -0.14
    ÑĢави
    -0.14
    amburger
    -0.14
    nika
    -0.14
    =".$_
    -0.13
    POSITIVE LOGITS
     options
    0.32
     possibilities
    0.31
     possible
    0.28
     option
    0.28
     Options
    0.24
     ваÑĢиан
    0.24
     possibility
    0.24
     possibile
    0.24
    options
    0.24
    Options
    0.24
    Act Density 0.368%

    No Known Activations