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

    Neuronpedia

    INDEX
    Explanations

    feedback related to user experience with software features and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.01
     CreateTagHelper
    -0.94
    mybatisplus
    -0.90
    oneofs
    -0.86
     للمعارف
    -0.86
     otomatig
    -0.79
    AddTagHelper
    -0.79
     fevere
    -0.77
    #+#
    -0.76
    fromnode
    -0.73
    POSITIVE LOGITS
     is
    1.32
     has
    1.06
     just
    0.98
     are
    0.94
     actually
    0.93
     also
    0.93
     still
    0.93
     always
    0.91
     was
    0.88
     can
    0.87
    Act Density 0.025%

    No Known Activations