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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and requirements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dispro
    -0.15
    185
    -0.15
    缮
    -0.14
    -scripts
    -0.14
     Maver
    -0.14
     DÆ°Æ¡ng
    -0.13
     Mah
    -0.13
    loff
    -0.13
    ίÏĥÏī
    -0.13
     Firm
    -0.13
    POSITIVE LOGITS
     applicable
    0.41
    -app
    0.21
    éģ©çĶ¨
    0.20
     applies
    0.19
    licable
    0.19
     Applies
    0.19
     aplic
    0.17
     appropriate
    0.16
     APPLY
    0.16
     lucky
    0.16
    Act Density 0.058%

    No Known Activations