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

    Neuronpedia

    INDEX
    Explanations

    qualifiers that indicate a degree of uncertainty or moderation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     somehow
    -0.18
    enet
    -0.17
    isable
    -0.15
    otropic
    -0.15
    s
    -0.15
    Atlas
    -0.15
    ses
    -0.15
    ÑģÑĤа
    -0.14
     irgend
    -0.14
    se
    -0.14
    POSITIVE LOGITS
    ewhat
    0.19
    esta
    0.16
    .ly
    0.16
    -more
    0.15
     æħ
    0.15
    ajar
    0.15
    /stdc
    0.15
    place
    0.15
    _FB
    0.15
    ãĤĪãģŃ
    0.14
    Act Density 0.011%

    No Known Activations