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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive determiners referring to unspecified entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'its' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tsy
    -0.84
    tch
    -0.84
    Gun
    -0.74
    roup
    -0.72
    amiya
    -0.70
    bys
    -0.68
    knife
    -0.66
    poke
    -0.65
    uls
    -0.65
    VS
    -0.64
    POSITIVE LOGITS
     contents
    1.27
     usefulness
    1.16
     importance
    1.16
     significance
    1.15
     origins
    1.13
     effects
    1.12
     implications
    1.09
     creator
    1.08
     predecessor
    1.08
     impact
    1.08
    Act Density 0.204%

    No Known Activations