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

    Neuronpedia

    INDEX
    Explanations

    terms related to architectural elements and structural features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Durant
    -0.17
     neighboring
    -0.16
    arpa
    -0.14
    лÑıÑħ
    -0.14
    ailable
    -0.14
    olit
    -0.13
    alat
    -0.13
    outil
    -0.13
    arger
    -0.13
    okol
    -0.13
    POSITIVE LOGITS
     Nos
    0.17
    IGO
    0.16
    Nos
    0.15
    еÑĢк
    0.15
    Align
    0.15
     aligned
    0.15
     keyed
    0.15
    hay
    0.15
    outh
    0.14
     alignment
    0.14
    Act Density 0.015%

    No Known Activations