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

    Neuronpedia

    INDEX
    Explanations

    mentions of strikes and protests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UILDER
    -0.17
     Podesta
    -0.16
    леÑĩ
    -0.15
    iture
    -0.15
    ÑĢап
    -0.15
    itures
    -0.15
    Trap
    -0.14
    RAP
    -0.14
     FileAccess
    -0.14
    -arrow
    -0.13
    POSITIVE LOGITS
     strike
    0.79
     Strike
    0.67
     strikes
    0.66
    strike
    0.59
    Strike
    0.58
     striking
    0.54
     Strikes
    0.51
     stri
    0.50
    _strike
    0.50
     struck
    0.48
    Act Density 0.091%

    No Known Activations