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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating direct and indirect relationships or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +:+
    -0.77
    "):
    -0.71
    forRoot
    -0.67
    "));
    -0.66
    '):
    -0.65
    '));
    -0.64
    ')):
    -0.64
    !");
    -0.64
    weli
    -0.63
    };*/
    -0.63
    POSITIVE LOGITS
     indirect
    1.38
     Indirect
    1.29
    indirect
    1.26
     indirectly
    1.26
    Indirect
    1.20
     indirec
    1.20
     direct
    0.89
     implicitly
    0.86
     roundabout
    0.82
    direct
    0.81
    Act Density 0.301%

    No Known Activations