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

    Neuronpedia

    INDEX
    Explanations

    phrases related to contrasting situations or consequences

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to winning and losing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.69
    cffffcc
    -0.68
     enthusi
    -0.66
     mathemat
    -0.65
     confir
    -0.64
     referen
    -0.64
    ccording
    -0.63
     misunder
    -0.61
    ntil
    -0.61
    Roaming
    -0.61
    POSITIVE LOGITS
     theirs
    1.07
     ours
    1.02
     hers
    0.99
     yours
    0.94
    ;}
    0.84
     mine
    0.81
    %;
    0.72
     elsewhere
    0.67
     others
    0.66
     è£ı
    0.65
    Act Density 0.821%

    No Known Activations