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

    Neuronpedia

    INDEX
    Explanations

    terms related to negative impacts and adverse effects, particularly in health and behavior contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     milagro
    -0.57
     referenties
    -0.57
     protoimpl
    -0.57
    WireFormatLite
    -0.56
    +#+#
    -0.55
    __":
    -0.55
    ConstraintMaker
    -0.54
    AsUp
    -0.53
     dusting
    -0.53
    NoError
    -0.52
    POSITIVE LOGITS
    mybatisplus
    0.74
     bad
    0.73
    👎
    0.71
     rossz
    0.69
    bad
    0.67
     foul
    0.65
     undesirable
    0.63
     adverse
    0.63
    Legături
    0.61
    nappropriate
    0.61
    Act Density 0.131%

    No Known Activations