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

    Neuronpedia

    INDEX
    Explanations

    words related to something being covered or concealed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "covered"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcsstore
    -0.76
    PUT
    -0.69
     Sabha
    -0.67
    RT
    -0.66
    assuming
    -0.65
    arb
    -0.63
    Lua
    -0.63
    jet
    -0.63
    ellen
    -0.63
    ZI
    -0.62
    POSITIVE LOGITS
     Coverage
    0.82
     cover
    0.81
     covering
    0.81
     covers
    0.81
    Cover
    0.80
     COVER
    0.78
    utical
    0.77
     covered
    0.77
    lees
    0.73
    undown
    0.73
    Act Density 0.017%

    No Known Activations