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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to pre-planned events or activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "planned."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upon
    -0.78
    inas
    -0.78
    ienced
    -0.77
    ĪĴ
    -0.77
    inches
    -0.76
    shire
    -0.73
    anca
    -0.72
    ysis
    -0.72
    è£ħ
    -0.72
    gars
    -0.71
    POSITIVE LOGITS
     Parenthood
    1.24
     pregnancies
    0.89
     obs
    0.89
    paren
    0.84
     rollout
    0.81
    escape
    0.78
     gestation
    0.78
     planned
    0.75
     vacations
    0.72
     itiner
    0.72
    Act Density 0.020%

    No Known Activations