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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political actions and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     our
    -0.52
    Whilst
    -0.51
     Whilst
    -0.51
    非常的
    -0.51
     possu
    -0.49
     veramente
    -0.49
     idag
    -0.47
     very
    -0.44
     navidad
    -0.44
     my
    -0.42
    POSITIVE LOGITS
    ніципалі
    0.76
     queſta
    0.73
     snippetHide
    0.73
    ſelf
    0.71
     nahilalakip
    0.69
     ſche
    0.66
    ésultats
    0.65
     Anſ
    0.64
    tagHelperRunner
    0.63
    featureID
    0.63
    Act Density 0.818%

    No Known Activations