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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a conditional relationship or a requirement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ples
    -0.72
    anza
    -0.66
    sg
    -0.63
    ���
    -0.62
     ende
    -0.62
    antha
    -0.62
    haw
    -0.61
    cludes
    -0.60
    calling
    -0.59
    erd
    -0.59
    POSITIVE LOGITS
    imental
    0.69
    istor
    0.69
    isphere
    0.69
    iments
    0.67
    itely
    0.64
    tumblr
    0.62
     yours
    0.60
    ICS
    0.60
    icons
    0.59
    icon
    0.58
    Act Density 0.010%

    No Known Activations