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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickey
    -0.17
    Aspect
    -0.15
    ppo
    -0.15
    cej
    -0.15
    urr
    -0.14
    qli
    -0.14
    олÑĸ
    -0.14
    hir
    -0.14
    ëħ
    -0.14
     disastr
    -0.14
    POSITIVE LOGITS
     further
    0.20
     details
    0.19
     soon
    0.19
     review
    0.17
     detail
    0.17
     next
    0.16
    eron
    0.16
     weiter
    0.16
     additional
    0.16
     Review
    0.15
    Act Density 0.145%

    No Known Activations