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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positive or supportive conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alm
    -0.17
    ibar
    -0.14
    steen
    -0.14
    SI
    -0.14
    ients
    -0.14
    ибли
    -0.14
    umped
    -0.14
     Chavez
    -0.14
    577
    -0.14
    lem
    -0.13
    POSITIVE LOGITS
    aller
    0.16
    agrant
    0.16
     Blonde
    0.15
     Overall
    0.14
     overall
    0.14
    ÃľRK
    0.14
    λοÏħ
    0.14
    ises
    0.14
    borough
    0.13
     Hoe
    0.13
    Act Density 0.030%

    No Known Activations