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

    Neuronpedia

    INDEX
    Explanations

    phrases that start with the word "something."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     становника
    -0.59
    parsedMessage
    -0.52
    EndContext
    -0.52
     někter
    -0.51
    InitVars
    -0.49
    ScopeManager
    -0.49
    这一点
    -0.48
    ものです
    -0.47
     allem
    -0.47
    BagConstraints
    -0.47
    POSITIVE LOGITS
     else
    1.13
    Else
    0.76
     ELSE
    0.73
    else
    0.73
     akin
    0.72
     Else
    0.69
     special
    0.67
    elif
    0.65
    ELSE
    0.60
     fishy
    0.59
    Act Density 0.118%

    No Known Activations