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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or typical behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sprá
    -0.58
     braccia
    -0.56
     Clements
    -0.53
     terpisah
    -0.52
     Bringing
    -0.51
     شدند
    -0.51
     ней
    -0.51
     labios
    -0.50
    akt
    -0.50
     Building
    -0.49
    POSITIVE LOGITS
     usually
    1.91
     Usually
    1.81
    Usually
    1.77
    usually
    1.67
     typically
    1.53
     Typically
    1.51
    Typically
    1.50
     normally
    1.49
    normally
    1.46
    typically
    1.44
    Act Density 0.153%

    No Known Activations