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

    Neuronpedia

    INDEX
    Explanations

    words related to specific actions being performed under certain conditions

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to singular occurrence and frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tre
    -0.93
    vous
    -0.69
    orio
    -0.68
    Dash
    -0.67
    ipation
    -0.66
    oka
    -0.66
    doms
    -0.63
    rite
    -0.63
    fell
    -0.63
     Congratulations
    -0.63
    POSITIVE LOGITS
     concurrently
    0.89
    andem
    0.81
     indoors
    0.80
     outdoors
    0.79
     consecut
    0.79
     disguised
    0.76
     extensively
    0.76
     aloud
    0.76
     sparing
    0.76
     abroad
    0.69
    Act Density 0.684%

    No Known Activations