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

    Neuronpedia

    INDEX
    Explanations

    phrases related to direction or orientation

    oai_token-act-pair · gpt-3.5-turbo

    references to directional movement or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esters
    -0.74
    aqu
    -0.73
    unker
    -0.73
    enty
    -0.70
    akov
    -0.69
    itted
    -0.68
    athered
    -0.67
    ighth
    -0.66
    iltr
    -0.66
     Surviv
    -0.65
    POSITIVE LOGITS
     direction
    1.24
    ality
    1.09
     directions
    1.09
     towards
    0.95
     toward
    0.93
    finding
    0.85
    finder
    0.84
     Direction
    0.83
    ward
    0.79
    ally
    0.79
    Act Density 0.038%

    No Known Activations