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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing opportunities, decisions, or significant moments for progression and growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -ap
    -0.16
     latter
    -0.15
    -ignore
    -0.15
    aram
    -0.15
    lobe
    -0.14
    paque
    -0.14
    oti
    -0.14
    ILLA
    -0.14
     Holt
    -0.13
    æľ«
    -0.13
    POSITIVE LOGITS
    -next
    0.19
    ,next
    0.18
     wave
    0.17
     Next
    0.17
    next
    0.16
    wave
    0.15
    -wave
    0.15
     next
    0.15
    Next
    0.15
    (next
    0.15
    Act Density 0.074%

    No Known Activations