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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial transactions and apparent information-seeking behavior

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to unspecified amounts or quantities of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.91
    abol
    -0.72
    ired
    -0.72
    raid
    -0.68
    yrinth
    -0.66
    emet
    -0.65
     reconstructed
    -0.65
     nicknamed
    -0.65
     incorrectly
    -0.64
    hung
    -0.63
    POSITIVE LOGITS
     extra
    1.00
     semblance
    0.96
    place
    0.87
     bucks
    0.82
     traction
    0.80
     spare
    0.80
     cushion
    0.79
     sanity
    0.77
     pointers
    0.76
     relief
    0.76
    Act Density 0.208%

    No Known Activations