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

    Neuronpedia

    INDEX
    Explanations

    references to attacks or aggressive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    attack or attacked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sidemargin
    -0.54
     незавершена
    -0.50
    eleste
    -0.49
    verständlich
    -0.47
    %)$
    -0.47
    compliance
    -0.46
    ніципалі
    -0.46
     zufolge
    -0.45
     Reverb
    -0.45
     mentorship
    -0.44
    POSITIVE LOGITS
     attacked
    0.99
     attacking
    0.94
    Attacking
    0.77
     atacado
    0.74
     atacar
    0.73
     attacc
    0.58
     menyerang
    0.55
     ataca
    0.54
     ATTACK
    0.54
    attack
    0.54
    Act Density 0.010%

    No Known Activations