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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical actions or movements involving various characters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     thut
    -1.27
     chong
    -1.24
     fte
    -1.23
     jati
    -1.21
     wherea
    -1.21
     bandung
    -1.21
     perciò
    -1.19
     fta
    -1.19
     ?...
    -1.19
     effe
    -1.17
    POSITIVE LOGITS
     in
    0.71
     In
    0.59
     IN
    0.59
     into
    0.58
    GEBURTS
    0.56
    in
    0.56
     <<<<<<<<<<<<<<
    0.55
    getIn
    0.55
    Bekijk
    0.53
    In
    0.53
    Act Density 0.204%

    No Known Activations