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

    Neuronpedia

    INDEX
    Explanations

    descriptions of complex systems with multiple components or functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ôt
    -0.15
    .paginator
    -0.14
    .cli
    -0.14
    abo
    -0.14
    ding
    -0.14
    bose
    -0.14
    ãģ¡
    -0.14
     sublicense
    -0.14
    orget
    -0.14
    semb
    -0.14
    POSITIVE LOGITS
     independent
    0.23
     identical
    0.22
     copies
    0.20
    antan
    0.19
     independ
    0.19
    copies
    0.19
    tier
    0.18
     Independent
    0.18
     parallel
    0.18
     layers
    0.18
    Act Density 0.150%

    No Known Activations