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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the composition or makeup of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isman
    -0.15
    alue
    -0.15
    Ñīик
    -0.15
    anson
    -0.14
    tti
    -0.14
    SerializedName
    -0.14
    shal
    -0.14
    alink
    -0.13
    ahren
    -0.13
    getc
    -0.13
    POSITIVE LOGITS
    625
    0.17
    adamente
    0.16
    raf
    0.15
    umen
    0.14
    ÑĥÑĢн
    0.14
    comb
    0.14
    fox
    0.13
    uter
    0.13
    иÑĨ
    0.13
    ÑĢог
    0.13
    Act Density 0.005%

    No Known Activations