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

    Neuronpedia

    INDEX
    Explanations

    terms related to "abrogation" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words starting with ab

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.70
     $_"
    -0.53
    stdc
    -0.52
     Inſ
    -0.52
    ésultats
    -0.52
     ainfi
    -0.51
    IntoConstraints
    -0.50
    ("")]
    -0.48
    ientras
    -0.48
     Conſ
    -0.47
    POSITIVE LOGITS
     ab
    1.22
     Ab
    1.21
    Ab
    1.15
     AB
    0.96
     Abi
    0.88
    ab
    0.82
     abz
    0.79
     ablation
    0.79
     Abby
    0.79
     Abel
    0.77
    Act Density 0.045%

    No Known Activations