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

    Neuronpedia

    INDEX
    Explanations

    instances where possessive forms are used

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Initialized
    -0.66
    Reviewer
    -0.62
    ":[
    -0.60
    rait
    -0.57
    rack
    -0.55
    rette
    -0.54
    sets
    -0.53
    =(
    -0.53
    ={
    -0.53
    quished
    -0.53
    POSITIVE LOGITS
     newest
    0.75
     own
    0.75
     finest
    0.71
    ullivan
    0.69
     footsteps
    0.68
     biggest
    0.66
     whereabouts
    0.65
     gonna
    0.65
     latest
    0.64
     favorite
    0.64
    Act Density 0.147%

    No Known Activations