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

    Neuronpedia

    INDEX
    Explanations

    phrases related to permissions and legal agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    боÑĤ
    -0.16
    agner
    -0.16
    anik
    -0.16
    YW
    -0.15
    rix
    -0.15
    aura
    -0.15
     GAP
    -0.14
    ucci
    -0.14
    IGNORE
    -0.14
    unik
    -0.14
    POSITIVE LOGITS
     use
    0.19
     freely
    0.17
     freedom
    0.16
     eccentric
    0.16
     permission
    0.16
     access
    0.15
     Jacob
    0.15
    299
    0.15
    cken
    0.14
    alth
    0.14
    Act Density 0.350%

    No Known Activations