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

    Neuronpedia

    INDEX
    Explanations

    words related to intersections or decision points

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cross" and its usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    姫
    -0.76
     Peb
    -0.74
    ERSON
    -0.72
    */(
    -0.70
    cffff
    -0.70
    idity
    -0.69
    auna
    -0.68
    URA
    -0.67
    nant
    -0.66
    tarian
    -0.65
    POSITIVE LOGITS
    roads
    1.13
    cross
    1.11
     cross
    0.98
    bows
    0.96
    bow
    0.89
    hair
    0.87
    Cross
    0.85
    bones
    0.82
     crosses
    0.81
     crossings
    0.80
    Act Density 0.009%

    No Known Activations