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

    Neuronpedia

    INDEX
    Explanations

    phrases related to important issues or priorities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to issues of priority and concern in societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apses
    -0.75
    icro
    -0.75
    apons
    -0.73
    onyms
    -0.73
    ancies
    -0.72
    ampires
    -0.72
    ansk
    -0.72
    ilipp
    -0.71
    archs
    -0.71
    arij
    -0.71
    POSITIVE LOGITS
     unto
    0.87
     fixture
    0.83
     reliever
    0.81
     occurrence
    0.70
     GOODMAN
    0.68
     starter
    0.67
     contributor
    0.66
     punishable
    0.66
    stay
    0.66
     deterrent
    0.66
    Act Density 0.180%

    No Known Activations