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

    Neuronpedia

    INDEX
    Explanations

    locations or objects situated in a specific corner

    oai_token-act-pair · gpt-3.5-turbo

    references to 'corner'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    guided
    -0.78
    odor
    -0.73
    jri
    -0.70
    uman
    -0.70
     paired
    -0.69
    atche
    -0.69
    etheus
    -0.68
    egal
    -0.67
    ploy
    -0.66
    hur
    -0.66
    POSITIVE LOGITS
     corner
    1.27
     corners
    1.10
    stones
    0.92
     Corner
    0.90
    chester
    0.80
    istas
    0.76
     guiActiveUnfocused
    0.74
    bies
    0.72
     Alley
    0.72
     Beir
    0.71
    Act Density 0.006%

    No Known Activations