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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistical performance in sports

    oai_token-act-pair · gpt-3.5-turbo

    the word "with" and its various occurrences in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insula
    -0.69
    mite
    -0.68
    mart
    -0.66
    orah
    -0.66
    icult
    -0.65
    hari
    -0.65
    ieri
    -0.63
    atel
    -0.62
    ]);
    -0.62
    strate
    -0.62
    POSITIVE LOGITS
    stood
    1.09
     regards
    1.03
     regard
    0.98
    drawn
    0.94
    draw
    0.93
    standing
    0.85
     impunity
    0.82
    holding
    0.80
     fists
    0.71
     ease
    0.70
    Act Density 0.138%

    No Known Activations