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

    Neuronpedia

    INDEX
    Explanations

    instances of character names and their corresponding actions or emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lesen
    -0.17
     fort
    -0.15
    žil
    -0.15
    طاÙĦ
    -0.14
    lexport
    -0.14
    avigate
    -0.14
    aÅŁ
    -0.14
    loor
    -0.14
    Å¡ti
    -0.14
    Äı
    -0.14
    POSITIVE LOGITS
    stå
    0.16
     seins
    0.15
    holm
    0.14
     naï
    0.14
    233
    0.14
    IGH
    0.13
    ricks
    0.13
     absence
    0.13
    arry
    0.13
    rick
    0.13
    Act Density 0.004%

    No Known Activations