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

    Neuronpedia

    INDEX
    Explanations

    words and terms related to quarrels and conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ian
    -0.18
    enia
    -0.18
    ing
    -0.17
    ively
    -0.16
    ema
    -0.16
    uxt
    -0.16
    uta
    -0.16
    ia
    -0.15
    iate
    -0.15
    iating
    -0.15
    POSITIVE LOGITS
     Quar
    0.26
     quar
    0.24
    antine
    0.22
    rels
    0.22
    /qu
    0.19
    uple
    0.16
    ANTA
    0.16
    term
    0.16
    -qu
    0.15
     quarantine
    0.15
    Act Density 0.006%

    No Known Activations