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

    Neuronpedia

    INDEX
    Explanations

    words with the letter sequence "eth" followed by a single character or space

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "e" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     slot
    -0.69
     Malays
    -0.66
     propensity
    -0.64
     ditch
    -0.61
     detail
    -0.60
     foss
    -0.59
     fragmentation
    -0.57
    ashtra
    -0.56
     directions
    -0.56
     tremend
    -0.56
    POSITIVE LOGITS
    lehem
    0.98
    zeb
    0.93
    qt
    0.86
    iful
    0.85
    aign
    0.82
    avior
    0.79
    eat
    0.74
    leck
    0.73
    mingham
    0.73
    ulf
    0.73
    Act Density 0.068%

    No Known Activations