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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ease or simplicity in various actions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mtree
    -0.16
    INTR
    -0.16
    mts
    -0.15
    prot
    -0.15
     prot
    -0.15
    umpt
    -0.14
    ÏİÏĤ
    -0.14
     ÐŁÑĢоÑĤ
    -0.14
    irc
    -0.14
     Diamond
    -0.14
    POSITIVE LOGITS
    antan
    0.17
    azen
    0.16
    boys
    0.15
    eyh
    0.15
    fell
    0.15
     dÃłng
    0.15
    uela
    0.14
    angelo
    0.14
    ausal
    0.14
    athan
    0.13
    Act Density 0.033%

    No Known Activations