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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "war" and its related terms, indicating discussions about conflict and military actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ede
    -0.17
    chen
    -0.16
     неÑģ
    -0.16
    ernal
    -0.15
    PERT
    -0.15
    enn
    -0.15
    ijo
    -0.15
    ular
    -0.15
    arity
    -0.14
    amiento
    -0.14
    POSITIVE LOGITS
    lord
    0.21
    rier
    0.20
    rior
    0.20
    lock
    0.20
    lords
    0.19
    far
    0.17
    fre
    0.16
    blers
    0.16
    locks
    0.16
    like
    0.16
    Act Density 0.040%

    No Known Activations