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

    Neuronpedia

    INDEX
    Explanations

    terms related to conflict and interpersonal strain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibur
    -0.74
    glas
    -0.68
    iolet
    -0.66
    utra
    -0.63
    umbn
    -0.62
    iverpool
    -0.61
    olphin
    -0.61
     advert
    -0.61
    ogo
    -0.61
     broch
    -0.60
    POSITIVE LOGITS
    lessly
    0.89
     between
    0.88
    uality
    0.86
     arising
    0.85
    less
    0.83
     friction
    0.82
     arises
    0.82
    relation
    0.82
    rained
    0.82
    locks
    0.82
    Act Density 0.020%

    No Known Activations