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

    Neuronpedia

    INDEX
    Explanations

    expressions of disbelief or skepticism regarding actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AddHtmlAttribute
    -0.69
     anſ
    -0.67
    chiha
    -0.65
    ništvo
    -0.64
     ſtate
    -0.62
     ergo
    -0.62
     alſo
    -0.61
     myſelf
    -0.60
     Chicano
    -0.59
     inſ
    -0.59
    POSITIVE LOGITS
     siquiera
    0.81
     even
    0.73
     remotely
    0.69
     barely
    0.65
     Even
    0.65
     EVEN
    0.64
    enumerate
    0.64
     CWE
    0.64
     ogóle
    0.61
    principalTable
    0.60
    Act Density 0.076%

    No Known Activations