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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ongoing or continuous actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     còn
    -0.17
    contin
    -0.17
     Continuing
    -0.16
    rzy
    -0.16
     continua
    -0.16
    acco
    -0.16
    ÑĩаÑģ
    -0.15
    ott
    -0.15
    енз
    -0.15
     continuing
    -0.15
    POSITIVE LOGITS
     down
    0.24
    ä¸ĭåİ»
    0.22
     unab
    0.19
     along
    0.19
     forward
    0.19
     with
    0.19
     efforts
    0.18
    ly
    0.17
     past
    0.17
     on
    0.16
    Act Density 0.044%

    No Known Activations