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

    Neuronpedia

    INDEX
    Explanations

    words related to proximity or close relationships

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "close" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NZ
    -0.82
    ãĥĨãĤ£
    -0.71
    ULE
    -0.68
    DOM
    -0.68
    Sov
    -0.68
    heim
    -0.67
    ICAN
    -0.66
    reme
    -0.66
    çī
    -0.66
    士
    -0.65
    POSITIVE LOGITS
     proximity
    1.01
     close
    0.93
     confinement
    0.85
     confid
    0.81
     minded
    0.77
     ties
    0.77
     closest
    0.76
     deadlines
    0.75
     enough
    0.75
     vicinity
    0.74
    Act Density 0.017%

    No Known Activations