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

    Neuronpedia

    INDEX
    Explanations

    words related to seeking shelter or protection

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "refuge" and related concepts of safety or sanctuary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    scope
    -0.76
    thin
    -0.75
    ym
    -0.73
    dule
    -0.70
    oths
    -0.69
    Eat
    -0.69
    APH
    -0.68
    oth
    -0.68
    ONES
    -0.68
    graph
    -0.67
    POSITIVE LOGITS
     refuge
    1.42
     Refuge
    1.13
    ctuary
    0.95
    ãĥķãĤ¡
    0.84
     sanctuary
    0.81
     shelter
    0.79
    ashtra
    0.76
     seeker
    0.76
    escape
    0.74
     seekers
    0.73
    Act Density 0.009%

    No Known Activations