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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific character strings or punctuation marks, particularly apostrophes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĮ
    -0.17
    sse
    -0.14
    ’n
    -0.14
    .FindGameObjectWithTag
    -0.14
    hra
    -0.14
    iddi
    -0.14
    mise
    -0.13
    év
    -0.13
    sher
    -0.13
    ãģ¡ãģ¯
    -0.13
    POSITIVE LOGITS
    uren
    0.18
    uria
    0.16
    ezier
    0.16
    ık
    0.16
    ullivan
    0.16
    âĶIJ
    0.16
     Shea
    0.15
    erb
    0.15
    nonce
    0.15
    pher
    0.15
    Act Density 0.026%

    No Known Activations