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

    Neuronpedia

    INDEX
    Explanations

    postures or positions involving assertion or dominance

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotions or desires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     strikingly
    -0.73
     respectively
    -0.71
     understandably
    -0.64
    ullah
    -0.62
     omin
    -0.59
     evidently
    -0.56
    Typically
    -0.56
    Published
    -0.56
    idges
    -0.56
     Historically
    -0.56
    POSITIVE LOGITS
     myself
    1.85
     my
    1.36
     thee
    1.10
     MY
    0.96
     yours
    0.93
     ya
    0.92
     mine
    0.87
     somet
    0.84
     them
    0.83
     THEM
    0.80
    Act Density 0.489%

    No Known Activations