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

    Neuronpedia

    INDEX
    Explanations

    words related to spatial orientation or positioning

    oai_token-act-pair · gpt-3.5-turbo

    terms related to orientation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.75
    女
    -0.73
    enegger
    -0.72
     Mellon
    -0.68
    asp
    -0.67
    isters
    -0.65
    otte
    -0.65
    wordpress
    -0.65
    icas
    -0.63
    KS
    -0.62
    POSITIVE LOGITS
    eering
    1.23
     orientation
    0.94
    xual
    0.81
    ï¸
    0.79
    ¥µ
    0.78
    irection
    0.75
    itudinal
    0.71
    ational
    0.71
    rient
    0.70
    GGGGGGGG
    0.69
    Act Density 0.046%

    No Known Activations