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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and their actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    原始内容存档于
    -0.42
    utives
    -0.35
     Infórmanos
    -0.34
    ôles
    -0.34
     témoins
    -0.33
     '\\;'
    -0.32
    ToTop
    -0.32
     bidders
    -0.32
    ticale
    -0.32
    терак
    -0.32
    POSITIVE LOGITS
     support
    1.16
     oppose
    1.10
     opposes
    1.09
     opposed
    1.07
    支持
    1.06
     supports
    1.02
     endorse
    0.99
    support
    0.99
     supporting
    0.98
     endorsing
    0.98
    Act Density 1.097%

    No Known Activations