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

    Neuronpedia

    INDEX
    Explanations

    adjectives and phrases that denote specific characteristics, orientations, or focuses related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undry
    -0.17
    duino
    -0.16
    phere
    -0.15
    chop
    -0.15
    mania
    -0.14
    uckets
    -0.14
    il
    -0.14
    æ§
    -0.14
    lef
    -0.14
    uga
    -0.14
    POSITIVE LOGITS
    ness
    0.19
    /-
    0.17
    lessly
    0.16
    NESS
    0.15
    eck
    0.15
    ạn
    0.15
     Barnett
    0.14
    ieten
    0.14
    ioned
    0.14
    790
    0.14
    Act Density 0.172%

    No Known Activations