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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "sun" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dorf
    -0.22
    enton
    -0.16
    gov
    -0.15
    964
    -0.15
    cheng
    -0.14
    opher
    -0.14
    cum
    -0.14
    leans
    -0.14
    cx
    -0.14
    omor
    -0.14
    POSITIVE LOGITS
    ken
    0.33
    flower
    0.31
    sets
    0.28
    flowers
    0.26
    burst
    0.26
    nier
    0.25
    niest
    0.25
     Microsystems
    0.25
    rise
    0.24
    screens
    0.24
    Act Density 0.025%

    No Known Activations