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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive forms

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to individuals or their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.92
    aughtered
    -0.84
     è£ıè
    -0.83
    reement
    -0.76
    Attach
    -0.75
    abeth
    -0.73
    isite
    -0.71
    ItemTracker
    -0.70
    "]=>
    -0.69
    PsyNetMessage
    -0.68
    POSITIVE LOGITS
     preach
    0.74
     jugg
    0.74
     coer
    0.73
     mul
    0.71
     exagger
    0.69
     sacrific
    0.68
     crus
    0.67
     preached
    0.67
     coy
    0.66
     preaching
    0.65
    Act Density 0.480%

    No Known Activations