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

    Neuronpedia

    INDEX
    Explanations

    references to safe places or havens

    oai_token-act-pair · gpt-3.5-turbo

    terms related to safe spaces or protective environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lass
    -0.90
    ahon
    -0.74
    othy
    -0.66
    iam
    -0.66
    omen
    -0.65
    isable
    -0.65
    ivan
    -0.65
    iple
    -0.65
    thin
    -0.65
    inness
    -0.63
    POSITIVE LOGITS
    ctuary
    0.79
     refuge
    0.76
     encl
    0.75
    bub
    0.72
     sanctuary
    0.71
     Refuge
    0.71
    mingham
    0.71
    pmwiki
    0.69
     havens
    0.68
     habitat
    0.67
    Act Density 0.085%

    No Known Activations