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

    Neuronpedia

    INDEX
    Explanations

    references to things being left behind or people being left behind

    oai_token-act-pair · gpt-3.5-turbo

    references to what is left or abandoned in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istic
    -0.70
     Pwr
    -0.70
    oret
    -0.67
    escal
    -0.66
    catentry
    -0.66
    odore
    -0.63
     Osw
    -0.62
    ynski
    -0.60
    acca
    -0.60
    andro
    -0.60
    POSITIVE LOGITS
     Runes
    0.69
    estern
    0.68
    stellar
    0.66
    ainers
    0.64
    vernment
    0.63
     Enemy
    0.63
    usha
    0.62
    âĸł
    0.61
    unity
    0.61
     refunds
    0.60
    Act Density 0.013%

    No Known Activations