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

    Neuronpedia

    INDEX
    Explanations

    words related to deductive reasoning or conclusions drawn from evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exas
    -0.14
     stray
    -0.14
    %S
    -0.14
    ypy
    -0.14
     prer
    -0.14
    .Pin
    -0.14
    elier
    -0.14
    ész
    -0.14
    å¾ĭ
    -0.14
    eller
    -0.14
    POSITIVE LOGITS
    uced
    0.27
    uce
    0.26
    icates
    0.25
    alus
    0.25
    icated
    0.23
    oose
    0.22
    UCE
    0.21
    ication
    0.20
    ucing
    0.19
    icator
    0.19
    Act Density 0.005%

    No Known Activations