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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference sequential steps or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansk
    -0.15
    åĻ¨
    -0.15
    ospel
    -0.15
    lio
    -0.15
    laps
    -0.14
    ILA
    -0.14
    lops
    -0.14
    chine
    -0.14
    anine
    -0.14
    wart
    -0.14
    POSITIVE LOGITS
    -door
    0.33
    -generation
    0.33
    /current
    0.26
    -gen
    0.24
     generation
    0.24
    door
    0.23
    -best
    0.23
     few
    0.23
    -next
    0.21
     steps
    0.20
    Act Density 0.050%

    No Known Activations