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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate movement or actions involving the word "out"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awtextra
    -0.83
    Pautan
    -0.80
     nahilalakip
    -0.76
     հղումներ
    -0.72
     unknownFields
    -0.72
    AsUp
    -0.72
     kaarangay
    -0.71
     Roskov
    -0.71
    rungsseite
    -0.70
    ThroughAttribute
    -0.70
    POSITIVE LOGITS
     cometh
    0.55
     vienen
    0.47
     brake
    0.46
    تق
    0.46
    、
    0.45
     castillo
    0.44
     ==
    0.44
     الحره
    0.44
     portée
    0.44
    laught
    0.44
    Act Density 0.076%

    No Known Activations