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

    Neuronpedia

    INDEX
    Explanations

    terms related to treatment and evaluation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unning
    -0.15
     Provision
    -0.15
    asant
    -0.15
    ammen
    -0.15
    RunWith
    -0.14
    ignet
    -0.14
    LOPT
    -0.14
    ();)
    -0.14
    arrings
    -0.14
     Qed
    -0.14
    POSITIVE LOGITS
    ood
    0.16
    overflow
    0.16
    ãĥĥãĥī
    0.15
    iso
    0.14
    ba
    0.14
    ault
    0.14
    /thread
    0.14
    hol
    0.14
    ologist
    0.14
     le
    0.13
    Act Density 0.175%

    No Known Activations