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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and requirements related to actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     account
    -0.44
     Equal
    -0.39
     EQUAL
    -0.36
    casian
    -0.36
     Pure
    -0.35
     Fairness
    -0.34
    <%=
    -0.34
    EQUAL
    -0.34
     Inclu
    -0.34
     Account
    -0.33
    POSITIVE LOGITS
     autorytatywna
    0.70
     needed
    0.63
    uxxxx
    0.60
    needed
    0.60
     nonUne
    0.60
     Infórmanos
    0.54
    ArgumentParser
    0.53
    afficheront
    0.52
     CreateTagHelper
    0.51
    addContainerGap
    0.49
    Act Density 0.406%

    No Known Activations