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

    Neuronpedia

    INDEX
    Explanations

    words related to shelter or protection

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "refuge" and related concepts of safety or shelter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    scope
    -0.76
    thin
    -0.75
    oths
    -0.74
    ym
    -0.73
    smoking
    -0.73
    oth
    -0.72
    dule
    -0.69
    ONES
    -0.69
    ammy
    -0.68
    authors
    -0.68
    POSITIVE LOGITS
     refuge
    1.34
     Refuge
    1.02
    ctuary
    0.96
     seeker
    0.76
    ashtra
    0.75
     sanctuary
    0.75
     seekers
    0.74
    itory
    0.72
    ãĥķãĤ¡
    0.71
    finder
    0.69
    Act Density 0.008%

    No Known Activations