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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating anticipation or promotion of something

    oai_token-act-pair · gpt-3.5-turbo

    prominent and repetitive phrases related to a specific season or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     skelet
    -0.75
     UNCLASSIFIED
    -0.72
    etheless
    -0.64
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.59
     Azerb
    -0.57
     exting
    -0.57
     disadvant
    -0.56
     cryst
    -0.54
     pse
    -0.54
     reper
    -0.54
    POSITIVE LOGITS
     [âĢ¦]
    0.69
     âĢİ
    0.68
    âĢİ
    0.58
    ↵Âł
    0.58
     ....
    0.53
     âĢº
    0.52
     ...
    0.48
     Downloads
    0.48
     Donald
    0.48
    ADVERTISEMENT
    0.47
    Act Density 5.957%

    No Known Activations