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

    Neuronpedia

    INDEX
    Explanations

    references to physical locations for which movement or transition is occurring

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "crossing" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wig
    -0.73
    nant
    -0.73
    andum
    -0.72
    etic
    -0.71
    enfranch
    -0.70
    alus
    -0.70
    abyte
    -0.67
    awk
    -0.66
    lance
    -0.66
    nesia
    -0.65
    POSITIVE LOGITS
     crossings
    1.24
     crossing
    1.16
    roads
    0.93
     Crossing
    0.90
     crosses
    0.82
     Sakuya
    0.79
    bows
    0.78
     Patrol
    0.78
    ortment
    0.78
     checkpoints
    0.74
    Act Density 0.007%

    No Known Activations