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

    Neuronpedia

    INDEX
    Explanations

    phrases related to invitations and participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iver
    -0.19
    vr
    -0.18
    IVER
    -0.16
    ãĤ¥
    -0.15
    ajs
    -0.15
    iah
    -0.14
     pozit
    -0.14
     universal
    -0.14
    bole
    -0.14
    drs
    -0.14
    POSITIVE LOGITS
    .easing
    0.17
    CodeAt
    0.16
    ongo
    0.14
    otten
    0.14
    CodeGen
    0.14
    zug
    0.14
    stoff
    0.13
    uchi
    0.13
    fav
    0.13
     Fernandez
    0.13
    Act Density 0.025%

    No Known Activations