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

    Neuronpedia

    INDEX
    Explanations

    phrases related to organizational tasks or procedures

    oai_token-act-pair · gpt-3.5-turbo

    references to events or gatherings involving community participation or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nutshell
    -0.63
     Inher
    -0.60
     hangs
    -0.56
    ģĸ
    -0.56
     capitalism
    -0.53
     revenge
    -0.52
     Capitalism
    -0.51
     engulf
    -0.51
     reborn
    -0.50
    ================================
    -0.50
    POSITIVE LOGITS
     apiece
    0.91
     respectively
    0.79
     desks
    0.77
     respective
    0.76
     microphones
    0.74
     predec
    0.72
     folders
    0.71
     scrut
    0.70
     booths
    0.70
     keyboards
    0.68
    Act Density 1.809%

    No Known Activations