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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating completeness or thoroughness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lo
    -0.19
    ning
    -0.18
    la
    -0.18
    land
    -0.18
    laws
    -0.17
     Wich
    -0.16
    rent
    -0.16
    ãģ¿
    -0.15
    rel
    -0.15
    .il
    -0.15
    POSITIVE LOGITS
     opposite
    0.18
    /full
    0.18
    itude
    0.18
    rosso
    0.16
    cec
    0.15
     strangers
    0.15
    ständ
    0.15
    ednou
    0.15
    mente
    0.15
    enance
    0.14
    Act Density 0.025%

    No Known Activations