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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional words that indicate relationships or connections in reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <?=$
    -0.65
     Efq
    -0.64
    apunov
    -0.64
    <?
    -0.64
     Dapper
    -0.63
     Hef
    -0.63
    stdc
    -0.61
    :///
    -0.59
     AssemblyProduct
    -0.58
     OnInit
    -0.58
    POSITIVE LOGITS
    ยว
    0.62
    AsUp
    0.60
    dymyr
    0.58
    TintMode
    0.57
    
    0.55
    empre
    0.55
     França
    0.55
    nowu
    0.54
     forth
    0.54
     importantly
    0.54
    Act Density 0.167%

    No Known Activations