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

    Neuronpedia

    INDEX
    Explanations

    dates or specific time-related information

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and terms related to time and place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uch
    -0.68
    river
    -0.65
    THIS
    -0.63
    yre
    -0.63
    ynes
    -0.60
     Souls
    -0.59
    irin
    -0.59
    imilar
    -0.58
    ¯¯¯¯
    -0.58
    tin
    -0.58
    POSITIVE LOGITS
     himself
    0.72
     ourselves
    0.67
     herself
    0.66
     itself
    0.65
     firsthand
    0.65
     themselves
    0.65
     its
    0.63
     myself
    0.62
     aloud
    0.61
    rer
    0.60
    Act Density 0.488%

    No Known Activations