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

    Neuronpedia

    INDEX
    Explanations

    references to physical corners within a physical space

    oai_token-act-pair · gpt-3.5-turbo

    references to "corner" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egal
    -0.81
    atoon
    -0.81
    inen
    -0.81
    hur
    -0.79
    ufact
    -0.77
    orthy
    -0.75
    emonic
    -0.74
    emon
    -0.73
    ignt
    -0.71
    uthor
    -0.71
    POSITIVE LOGITS
    stones
    1.11
    bars
    0.88
     corner
    0.85
     corners
    0.83
    naire
    0.82
    busters
    0.81
    paper
    0.73
    chester
    0.73
     Brook
    0.67
    kick
    0.66
    Act Density 0.021%

    No Known Activations