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

    Neuronpedia

    INDEX
    Explanations

    words related to isolation or being separate from others

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of isolation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orah
    -0.93
    enegger
    -0.84
    vous
    -0.77
    rote
    -0.76
    ãĥ£
    -0.74
    igel
    -0.69
    herty
    -0.68
    Benz
    -0.67
    eor
    -0.66
    rouse
    -0.64
    POSITIVE LOGITS
     isolation
    1.19
     wards
    0.83
    olation
    0.80
     confinement
    0.78
    ism
    0.77
    uous
    0.76
     plat
    0.73
     isol
    0.73
    yip
    0.72
    ively
    0.69
    Act Density 0.009%

    No Known Activations