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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest a surprising or impactful experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    нина
    -0.15
    á»ģn
    -0.15
    umbed
    -0.15
    iaux
    -0.15
     Voting
    -0.14
    mitter
    -0.14
    ÑĩиÑħ
    -0.14
    rient
    -0.14
    εί
    -0.14
    errupted
    -0.14
    POSITIVE LOGITS
     Perry
    0.18
    ÑĨенÑĤ
    0.15
    uther
    0.15
    ichni
    0.14
    rotch
    0.14
    /vector
    0.14
    link
    0.14
    ordo
    0.14
    me
    0.13
     uz
    0.13
    Act Density 0.289%

    No Known Activations