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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making amends or fulfilling obligations

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the concept of quality or goodness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.74
    anwhile
    -0.67
     Huntington
    -0.64
     Sloan
    -0.60
    ngth
    -0.58
     Strauss
    -0.58
    enne
    -0.58
     Greenwood
    -0.58
    ":["
    -0.57
    ennial
    -0.56
    POSITIVE LOGITS
    sense
    0.76
     impression
    0.66
    sett
    0.65
     dent
    0.63
     advances
    0.62
    roads
    0.59
     ende
    0.59
     mockery
    0.59
     landfall
    0.58
    nell
    0.58
    Act Density 0.070%

    No Known Activations