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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    contextual references to specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     coerc
    -0.69
    ."[
    -0.68
    ".[
    -0.63
     withdraw
    -0.62
     withdrew
    -0.60
     withdrawing
    -0.59
    ertodd
    -0.58
     dumps
    -0.57
    ).[
    -0.57
     contrace
    -0.56
    POSITIVE LOGITS
    icion
    0.92
     understatement
    0.70
     geek
    0.68
    erning
    0.65
     nerd
    0.64
     intrigued
    0.63
    Fans
    0.63
     cringe
    0.62
    Legend
    0.61
     fans
    0.61
    Act Density 1.087%

    No Known Activations