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

    Neuronpedia

    INDEX
    Explanations

    superlative forms and phrases emphasizing "most" in relation to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odesk
    -0.15
    erner
    -0.15
    ÂĽ
    -0.15
    undler
    -0.14
    ayne
    -0.14
    eka
    -0.14
    amping
    -0.14
    å±ŀ
    -0.14
    raison
    -0.14
    éĥ½å¸Ĥ
    -0.14
    POSITIVE LOGITS
     talked
    0.23
    -talk
    0.23
     successful
    0.20
    -ce
    0.19
    decor
    0.18
     succes
    0.17
     influ
    0.17
    cov
    0.17
     fec
    0.17
     respected
    0.17
    Act Density 0.067%

    No Known Activations