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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating financial consequences or negative evaluations of projects and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.73
    AndEndTag
    -0.73
    CompleteListener
    -0.72
    OOTDTY
    -0.71
     againſt
    -0.69
    mybatisplus
    -0.67
     estekak
    -0.66
    Abitanti
    -0.64
    Przypisy
    -0.63
     meriva
    -0.60
    POSITIVE LOGITS
     disaster
    0.70
     nightmare
    0.61
     Disaster
    0.60
     ticking
    0.59
    潭
    0.57
    Disaster
    0.57
    kang
    0.57
    disaster
    0.56
     catastrophe
    0.53
     tra
    0.53
    Act Density 0.276%

    No Known Activations