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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    go ahead and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sekä
    -0.68
     maupun
    -0.67
     valamint
    -0.63
     sowie
    -0.57
     ainsi
    -0.56
     illetve
    -0.55
    ResumeLayout
    -0.51
     nonché
    -0.49
    sowie
    -0.49
     وكذلك
    -0.49
    POSITIVE LOGITS
    并
    0.88
    並
    0.74
     并
    0.66
    して
    0.64
    并在
    0.60
     ולה
    0.57
     وتح
    0.54
     並
    0.53
    StateToProps
    0.52
    enterOuterAlt
    0.50
    Act Density 0.361%

    No Known Activations