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

    Neuronpedia

    INDEX
    Explanations

    mentions of strategic plans or proposals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "plan" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.72
    ibaba
    -0.64
    leaning
    -0.63
     ILCS
    -0.62
     Stain
    -0.61
    ruciating
    -0.61
    safety
    -0.61
    ADRA
    -0.61
    å°Ĩ
    -0.60
    amped
    -0.60
    POSITIVE LOGITS
    isphere
    0.95
    emaker
    0.90
    ters
    0.88
     2030
    0.79
    meal
    0.76
    escape
    0.76
    ets
    0.71
    fare
    0.71
    urally
    0.70
    atives
    0.68
    Act Density 0.039%

    No Known Activations