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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical movement and positioning

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to spatial movement or positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     staffers
    -0.65
    named
    -0.64
     aspiring
    -0.63
     bloggers
    -0.61
     deleg
    -0.61
     pundits
    -0.61
    eni
    -0.61
    ¶ħ
    -0.59
     politicians
    -0.59
    ician
    -0.58
    POSITIVE LOGITS
     orbit
    1.21
     seiz
    1.01
     bounds
    1.01
     captivity
    1.01
    animate
    0.94
     position
    0.93
     orbits
    0.93
     range
    0.92
     vicinity
    0.91
     proximity
    0.90
    Act Density 0.260%

    No Known Activations