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

    Neuronpedia

    INDEX
    Explanations

    phrases representing the movement or transfer from one place, state, or condition to another

    oai_token-act-pair · gpt-3.5-turbo

    repetitive mentions of the word "another" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uci
    -0.64
     Rockets
    -0.63
    letters
    -0.61
     Texans
    -0.60
     Motorsport
    -0.60
    Ŀ
    -0.59
    nit
    -0.59
    °
    -0.59
    lux
    -0.59
    speak
    -0.58
    POSITIVE LOGITS
    isphere
    0.79
     depending
    0.79
    dayName
    0.78
     consecut
    0.74
     lobe
    0.74
    esthetic
    0.71
     across
    0.71
    inant
    0.70
     vowel
    0.69
     wart
    0.69
    Act Density 0.061%

    No Known Activations