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

    Neuronpedia

    INDEX
    Explanations

    the word "ser" followed by a number, potentially as part of a series or list

    oai_token-act-pair · gpt-3.5-turbo

    words related to services or sacrificial themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INGTON
    -0.80
    ORE
    -0.76
    ORED
    -0.75
    ITNESS
    -0.72
    hetti
    -0.72
    å¯
    -0.72
    OWS
    -0.71
     Parkinson
    -0.70
    ORN
    -0.70
     Allies
    -0.69
    POSITIVE LOGITS
    geant
    1.09
     confir
    1.02
     ser
    0.93
     encount
    0.88
    ials
    0.88
    iffs
    0.86
     tyr
    0.85
    itage
    0.85
    ogly
    0.85
    iatrics
    0.80
    Act Density 0.005%

    No Known Activations