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

    Neuronpedia

    INDEX
    Explanations

    words related to various household objects and activities

    oai_token-act-pair · gpt-3.5-turbo

    words related to containers or receptacles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paces
    -0.73
    actionDate
    -0.70
    phen
    -0.67
    ontent
    -0.67
    ãĥ©ãĥ³
    -0.67
    é¾
    -0.67
     Flavoring
    -0.65
    erenn
    -0.65
     Elven
    -0.64
     Childhood
    -0.63
    POSITIVE LOGITS
     malfunction
    0.89
     operator
    0.86
     operated
    0.83
     operators
    0.79
     nozzle
    0.78
     doors
    0.77
     pumps
    0.76
     blades
    0.75
    lift
    0.75
    pipe
    0.74
    Act Density 0.204%

    No Known Activations