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

    Neuronpedia

    INDEX
    Explanations

    numbers and codes

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and abbreviations related to specific identifiers or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rar
    -0.63
     Amend
    -0.61
     Pruitt
    -0.61
    Nik
    -0.60
    rade
    -0.59
     Garner
    -0.59
    mat
    -0.59
    aved
    -0.58
     Stephens
    -0.58
    rez
    -0.58
    POSITIVE LOGITS
     itself
    0.79
     inhibitors
    0.70
     Syndrome
    0.66
     Citadel
    0.61
     syndrome
    0.60
     bandwagon
    0.59
     herself
    0.58
    's
    0.57
     Implementation
    0.57
     aloud
    0.57
    Act Density 0.412%

    No Known Activations