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

    Neuronpedia

    INDEX
    Explanations

    sentences related to changes in circumstances or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     of
    -0.50
    ням
    -0.46
     pob
    -0.46
    Replacing
    -0.45
     bort
    -0.45
    ium
    -0.45
    [
    -0.44
    たら
    -0.44
    ,
    -0.44
      
    -0.43
    POSITIVE LOGITS
     things
    1.15
    Things
    1.12
    things
    1.06
     $_"
    1.06
     Things
    1.05
    ſelf
    1.04
     surla
    1.04
    THINGS
    1.03
     THINGS
    0.99
     itſelf
    0.91
    Act Density 0.140%

    No Known Activations