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

    Neuronpedia

    INDEX
    Explanations

    phrases related to arrivals and destinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADATA
    -0.17
    opal
    -0.14
    /goto
    -0.14
    teg
    -0.14
    reece
    -0.14
    gone
    -0.14
    ecess
    -0.14
    zap
    -0.14
    REEN
    -0.13
    segue
    -0.13
    POSITIVE LOGITS
     arrive
    0.82
     arrived
    0.79
     arrival
    0.77
     arrives
    0.75
     arriving
    0.68
     arriv
    0.68
     Arr
    0.62
     arrivals
    0.61
    arr
    0.60
     Arrival
    0.60
    Act Density 0.266%

    No Known Activations