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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the expression "used to."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express past habits or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oval
    -0.80
    IDA
    -0.72
    edIn
    -0.71
    ð
    -0.71
    unal
    -0.70
    ares
    -0.69
     Expansion
    -0.67
    impro
    -0.65
    soever
    -0.65
    leaf
    -0.64
    POSITIVE LOGITS
     joke
    1.15
     haunt
    1.01
     tease
    0.95
     be
    0.92
     adore
    0.90
     roam
    0.89
     flock
    0.88
     hate
    0.87
     dominate
    0.87
     laugh
    0.86
    Act Density 0.059%

    No Known Activations