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

    Neuronpedia

    INDEX
    Explanations

    negative prefixes in adjectives and adverbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    964
    -0.15
     budd
    -0.15
    visibility
    -0.14
    _visibility
    -0.14
     Sang
    -0.14
    มาà¸ģ
    -0.14
     late
    -0.14
    293
    -0.13
     anonymity
    -0.13
    俺ãģ¯
    -0.13
    POSITIVE LOGITS
    ecessarily
    0.20
    conv
    0.20
    character
    0.18
    orth
    0.17
    enth
    0.17
    Conv
    0.16
    ortho
    0.15
    Ïİνα
    0.15
     Conv
    0.15
     appet
    0.15
    Act Density 0.025%

    No Known Activations