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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating investigation or consideration

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "look into."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bender
    -0.67
     farewell
    -0.65
    ienne
    -0.64
    eat
    -0.62
     rightfully
    -0.60
    patrick
    -0.58
    hop
    -0.58
     insistence
    -0.57
     reluct
    -0.57
    stick
    -0.56
    POSITIVE LOGITS
    clusion
    0.70
     feasibility
    0.68
    zag
    0.65
     infinity
    0.65
    vernment
    0.63
    âĸijâĸij
    0.62
    dfx
    0.61
    actionDate
    0.60
     Angle
    0.60
    iti
    0.60
    Act Density 0.026%

    No Known Activations