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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve expansion or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipt
    -0.14
    uate
    -0.14
    ecer
    -0.14
    leme
    -0.14
     Rosenstein
    -0.14
    -0.13
    ç¦ģ
    -0.13
    ç¾
    -0.13
    avo
    -0.13
    ibe
    -0.13
    POSITIVE LOGITS
     ones
    0.22
     usual
    0.21
     being
    0.19
    olley
    0.18
     already
    0.18
    usual
    0.17
    enger
    0.16
     каж
    0.16
    already
    0.16
    regular
    0.16
    Act Density 0.029%

    No Known Activations