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

    Neuronpedia

    INDEX
    Explanations

    expressions emphasizing significance or particularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑģÑı
    -0.15
    adam
    -0.15
    tright
    -0.14
    illin
    -0.14
    amarin
    -0.14
    zk
    -0.14
    chnitt
    -0.14
    ogan
    -0.13
    adel
    -0.13
    indow
    -0.13
    POSITIVE LOGITS
     ones
    0.21
     those
    0.16
    ones
    0.16
     Ones
    0.15
    efa
    0.15
     when
    0.15
    eslint
    0.14
     revolving
    0.13
     Bracket
    0.13
     Shir
    0.13
    Act Density 0.024%

    No Known Activations