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

    Neuronpedia

    INDEX
    Explanations

    phrases and contexts related to making decisions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     occhiali
    -0.89
    ContentAlignment
    -0.84
    ंदीखरीदारी
    -0.81
     direitos
    -0.81
     titolata
    -0.81
     $_"
    -0.81
     comigo
    -0.80
    writeFieldEnd
    -0.80
     FileInputStream
    -0.79
    PreferredItem
    -0.79
    POSITIVE LOGITS
     made
    1.66
     make
    1.63
     MAKE
    1.53
    make
    1.53
    made
    1.51
     Make
    1.50
    Make
    1.48
     MADE
    1.47
    Made
    1.43
     Made
    1.42
    Act Density 0.254%

    No Known Activations