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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or lack of clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Selectable
    -0.16
    ppo
    -0.14
    not
    -0.14
    inos
    -0.14
    oci
    -0.14
    omer
    -0.13
    ære
    -0.13
    iore
    -0.13
    erek
    -0.13
    lat
    -0.13
    POSITIVE LOGITS
     whether
    0.23
     precise
    0.22
    æĺ¯åIJ¦
    0.21
     exact
    0.21
     details
    0.20
    whether
    0.20
     exactly
    0.20
     precisely
    0.19
     æĺ¯åIJ¦
    0.18
    exact
    0.18
    Act Density 0.065%

    No Known Activations