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

    Neuronpedia

    INDEX
    Explanations

    words related to spatial positioning or physical orientation

    oai_token-act-pair · gpt-3.5-turbo

    references to angles and their variations or implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alty
    -0.77
    TB
    -0.70
    eele
    -0.68
    PDATE
    -0.68
    eah
    -0.68
    atile
    -0.67
    uum
    -0.66
    omin
    -0.66
    essee
    -0.65
    itative
    -0.65
    POSITIVE LOGITS
    weed
    0.92
    angle
    0.79
     sling
    0.74
    hawk
    0.72
     Arms
    0.72
     carrot
    0.72
    weight
    0.71
    angled
    0.70
     bikini
    0.69
     dangling
    0.69
    Act Density 0.022%

    No Known Activations