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

    Neuronpedia

    INDEX
    Explanations

    important locations and focal points within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olle
    -0.16
    новид
    -0.15
    iez
    -0.15
    cdc
    -0.14
     تÙĪس
    -0.13
    inen
    -0.13
    uren
    -0.13
    ings
    -0.13
     Sawyer
    -0.13
    .FLAG
    -0.13
    POSITIVE LOGITS
     attention
    0.24
     gravity
    0.24
     activity
    0.22
     everything
    0.22
    gravity
    0.21
     Attention
    0.20
     hub
    0.19
    point
    0.19
     Gravity
    0.19
     universe
    0.19
    Act Density 0.062%

    No Known Activations