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

    Neuronpedia

    INDEX
    Explanations

    references to deliberate actions and their consequences, particularly in the context of violence or injury

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibil
    -0.18
    iqu
    -0.15
    ique
    -0.15
     accompany
    -0.14
    posure
    -0.14
    otland
    -0.14
    orthand
    -0.14
    éĿ©
    -0.14
     firefight
    -0.14
    blink
    -0.14
    POSITIVE LOGITS
     hit
    0.39
     ram
    0.32
    hit
    0.31
     hits
    0.30
    Hit
    0.30
     Hit
    0.28
     HIT
    0.28
    æĴ
    0.27
     hitting
    0.27
    -hit
    0.26
    Act Density 0.076%

    No Known Activations