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

    Neuronpedia

    INDEX
    Explanations

    references to future events or timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sis
    -0.20
    ses
    -0.17
    ritch
    -0.17
    spath
    -0.16
     early
    -0.16
    ervals
    -0.16
    Powered
    -0.15
    nout
    -0.15
    sb
    -0.15
    rosso
    -0.15
    POSITIVE LOGITS
    ally
    0.33
    ality
    0.30
    -stage
    0.29
     stages
    0.25
    ALLY
    0.23
    -day
    0.22
    -than
    0.21
    als
    0.21
    -life
    0.19
    most
    0.19
    Act Density 0.020%

    No Known Activations