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

    Neuronpedia

    INDEX
    Explanations

    instances of positive or reinforcing expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     initComponents
    -0.77
     ker
    -0.72
     kira
    -0.67
    </i>
    -0.67
    Hawks
    -0.66
     kas
    -0.65
     Sark
    -0.65
    Lindsay
    -0.65
     cas
    -0.64
    .
    -0.63
    POSITIVE LOGITS
    &+
    1.54
    >+</
    1.51
    }+
    1.38
     +
    1.37
    ()+
    1.35
    )+
    1.32
    _+
    1.30
     $+
    1.29
    %+
    1.28
    +
    1.27
    Act Density 0.453%

    No Known Activations