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

    Neuronpedia

    INDEX
    Explanations

    negative descriptors related to moral outrage and tragedy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.77
    tagHelperRunner
    -0.66
     الرياضيه
    -0.63
    Personendaten
    -0.61
     vooz
    -0.57
     queſta
    -0.57
     queſto
    -0.57
    <unused43>
    -0.57
     encre
    -0.56
    <unused8>
    -0.56
    POSITIVE LOGITS
     horrifying
    0.87
     horrific
    0.87
     disgusting
    0.81
     horrors
    0.77
     horrible
    0.77
     horror
    0.77
     horrified
    0.74
     appalling
    0.72
     horrendous
    0.70
     hideous
    0.66
    Act Density 0.187%

    No Known Activations