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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or simile

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kate
    -0.17
     Hayward
    -0.16
    benh
    -0.16
    851
    -0.15
    kovi
    -0.15
    abay
    -0.15
    Å¡k
    -0.14
    ãĤ¯ãĤ»
    -0.14
     Dann
    -0.14
    akh
    -0.14
    POSITIVE LOGITS
     possible
    0.32
     Possible
    0.26
    possible
    0.24
     posible
    0.23
    _possible
    0.23
    Possible
    0.22
     possÃŃvel
    0.21
     possibile
    0.21
    ammo
    0.20
    åı¯èĥ½
    0.20
    Act Density 0.027%

    No Known Activations