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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and verbs related to action or development

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Secondly
    -0.92
    Furthermore
    -0.90
    Additionally
    -0.89
    sequently
    -0.78
    Moreover
    -0.78
    Materials
    -0.76
    ONSORED
    -0.75
    >>>
    -0.71
     thereafter
    -0.71
     Secondly
    -0.70
    POSITIVE LOGITS
     buzzing
    0.86
     rejoice
    0.86
     awfully
    0.84
     famously
    0.74
     clich
    0.74
     sexy
    0.74
     understatement
    0.73
     thrilled
    0.73
     haunted
    0.72
     love
    0.72
    Act Density 0.552%

    No Known Activations