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

    Neuronpedia

    INDEX
    Explanations

    words related to names and labels

    oai_token-act-pair · gpt-3.5-turbo

    words related to naming or renaming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.69
     confir
    -0.68
     nib
    -0.65
     holster
    -0.64
     denial
    -0.63
     prescription
    -0.61
     incon
    -0.61
     bondage
    -0.60
     retreating
    -0.59
     rehab
    -0.59
    POSITIVE LOGITS
    aming
    1.51
    ame
    1.44
    ames
    1.35
    amed
    1.25
    fleet
    0.98
    amia
    0.97
    AME
    0.91
    amn
    0.89
    plates
    0.83
    erous
    0.82
    Act Density 0.005%

    No Known Activations