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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "it" and sentence openings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Obrigada
    -0.65
    basicConfig
    -0.60
    atouille
    -0.57
    rosoft
    -0.56
    ranath
    -0.55
    ertale
    -0.54
     penguin
    -0.53
     Kapit
    -0.53
     lasso
    -0.52
     fMRI
    -0.52
    POSITIVE LOGITS
    帖最后由
    0.63
     fellas
    0.58
    .......
    0.58
    ........
    0.57
    łem
    0.56
    Gentlemen
    0.55
    hobby
    0.55
    .....
    0.55
    forums
    0.54
     skall
    0.54
    Act Density 0.517%

    No Known Activations