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

    Neuronpedia

    INDEX
    Explanations

    terms related to decrease or decline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etter
    -0.75
    rah
    -0.70
    ilda
    -0.67
    breakers
    -0.67
    sol
    -0.66
    eering
    -0.66
    atom
    -0.64
    raid
    -0.64
    è¦ļéĨĴ
    -0.63
    swick
    -0.63
    POSITIVE LOGITS
     violet
    0.80
     footprint
    0.76
     effectiveness
    0.75
    owship
    0.74
     visibility
    0.73
     stature
    0.72
     consciousness
    0.72
     clout
    0.71
     appetite
    0.71
    utive
    0.71
    Act Density 0.022%

    No Known Activations