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

    Neuronpedia

    INDEX
    Explanations

    the word "alone" or variations of it in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being alone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aminer
    -0.85
    eme
    -0.81
    older
    -0.73
    aptic
    -0.72
     pse
    -0.72
    andum
    -0.70
    MER
    -0.68
    amac
    -0.66
    ulate
    -0.66
    ickr
    -0.66
    POSITIVE LOGITS
     confinement
    0.72
     Alone
    0.70
    hall
    0.66
    alone
    0.62
    icated
    0.62
    heim
    0.61
    handedly
    0.61
     indoors
    0.61
    kat
    0.60
     else
    0.59
    Act Density 0.031%

    No Known Activations