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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is alone

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "alone."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickr
    -0.80
    nant
    -0.72
    EMP
    -0.70
    aptic
    -0.70
     pse
    -0.67
    UTC
    -0.67
    ourses
    -0.67
     fracturing
    -0.66
    rise
    -0.65
    um
    -0.65
    POSITIVE LOGITS
     alone
    1.01
     Alone
    0.88
    alone
    0.78
    cule
    0.76
    soever
    0.68
     unaccompanied
    0.67
    assisted
    0.64
    lihood
    0.62
    stretched
    0.60
     Sacrifice
    0.59
    Act Density 0.012%

    No Known Activations