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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social interactions and group activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ¦↵
    -0.28
    âĢ¦and
    -0.25
    âĢ¦”
    -0.24
    âĢ¦
    -0.23
    âĢ¦.
    -0.22
     âĢ¦↵
    -0.22
    âĢ¦I
    -0.21
    âĢ¦the
    -0.21
    âĢ¦but
    -0.21
    âĢ¦âĢ¦
    -0.21
    POSITIVE LOGITS
    #af
    0.16
    #ab
    0.16
    #ac
    0.16
    #ad
    0.15
     -*-č↵
    0.15
    )frame
    0.14
    )application
    0.14
    #aa
    0.14
    @js
    0.14
    /******/
    0.13
    Act Density 98.153%

    No Known Activations