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

    Neuronpedia

    INDEX
    Explanations

    legal and administrative actions related to decisions and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Vidite
    -0.45
    Throughout
    -0.41
     jota
    -0.40
     throughout
    -0.40
     Throughout
    -0.40
    DidLoad
    -0.39
    throughout
    -0.38
     taba
    -0.36
    enseits
    -0.36
    additional
    -0.35
    POSITIVE LOGITS
     altogether
    1.09
     abruptly
    0.89
     permanently
    0.88
     навсегда
    0.84
     uncer
    0.84
     forever
    0.83
     leaving
    0.80
     prematurely
    0.74
     gracefully
    0.74
     entirely
    0.69
    Act Density 0.799%

    No Known Activations