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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing continuation or elaboration in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.75
    AnchorStyles
    -0.71
    featureID
    -0.60
    TypedDataSet
    -0.59
    
    -0.58
    ########.
    -0.55
     tarko
    -0.55
    Portail
    -0.54
    ]")]
    -0.54
    
    -0.52
    POSITIVE LOGITS
     etc
    0.81
     Etc
    0.78
    etc
    0.73
    之类的
    0.71
    Etc
    0.69
     usw
    0.68
     stb
    0.66
     ETC
    0.65
     noqa
    0.65
     आदि
    0.64
    Act Density 0.234%

    No Known Activations