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

    Neuronpedia

    INDEX
    Explanations

    specific special character sequences or sequences of non-standard characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hacked
    -0.15
     اخÙĦاÙĤ
    -0.13
     stolen
    -0.13
     Hacker
    -0.12
    inyin
    -0.12
    ipient
    -0.12
    aginator
    -0.12
     Timeline
    -0.12
    éĤª
    -0.12
    area
    -0.12
    POSITIVE LOGITS
     declaration
    0.28
     announcement
    0.28
     departure
    0.27
     dismissal
    0.26
     ascent
    0.26
     assertion
    0.25
     proclamation
    0.25
     depiction
    0.24
     withdrawal
    0.24
     dissolution
    0.24
    Act Density 0.055%

    No Known Activations