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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "monolith" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    led
    -0.16
    -0.15
    cred
    -0.14
    iability
    -0.14
    istry
    -0.14
    oglobin
    -0.14
     addObject
    -0.14
    enger
    -0.14
    ë¹ĦìĬ¤
    -0.14
    iku
    -0.13
    POSITIVE LOGITS
    oton
    0.19
    .Mon
    0.19
    елÑĮзÑı
    0.17
     behalf
    0.17
    Mono
    0.16
    itored
    0.16
    aco
    0.16
    oxel
    0.16
    (mon
    0.16
    aghan
    0.16
    Act Density 0.057%

    No Known Activations