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

    Neuronpedia

    INDEX
    Explanations

    adjectives denoting appearance or perspective

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and its variations, as well as similar articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olid
    -0.54
    Joined
    -0.53
    iasm
    -0.52
    undo
    -0.52
    ulsion
    -0.52
     Remem
    -0.51
     persever
    -0.50
    Inst
    -0.50
     dep
    -0.50
     Kurdistan
    -0.49
    POSITIVE LOGITS
    heit
    0.74
     way
    0.69
     slightest
    0.66
    gh
    0.65
    course
    0.63
    $$
    0.63
    ily
    0.61
    Course
    0.60
    uously
    0.60
    SHIP
    0.59
    Act Density 0.154%

    No Known Activations