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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or desires

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or the act of having something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilon
    -0.67
     Bounty
    -0.65
     coward
    -0.62
     Kov
    -0.62
    Line
    -0.60
    adj
    -0.60
    hooting
    -0.59
     Nort
    -0.58
    gradient
    -0.57
    \/\/
    -0.57
    POSITIVE LOGITS
     conversation
    0.78
     impact
    0.76
     haircut
    0.76
     rethink
    0.73
    icum
    0.67
    oided
    0.66
     WRITE
    0.66
    ipolar
    0.65
    readable
    0.65
    ctic
    0.65
    Act Density 0.240%

    No Known Activations