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

    Neuronpedia

    INDEX
    Explanations

    terms related to combat or fighting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñīик
    -0.18
    /right
    -0.17
    sis
    -0.17
     perv
    -0.16
    ulis
    -0.16
    holders
    -0.15
    à¥Īस
    -0.15
     aspir
    -0.15
    hell
    -0.15
    holder
    -0.15
    POSITIVE LOGITS
    ant
    0.42
    ants
    0.41
    ting
    0.31
    iveness
    0.28
    ANT
    0.27
    ANTS
    0.24
    -zone
    0.22
    anten
    0.21
    ual
    0.21
    ative
    0.20
    Act Density 0.008%

    No Known Activations