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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or typicality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     phosp
    -0.43
    IGraphics
    -0.43
     melons
    -0.42
    getch
    -0.42
    WriteLiteral
    -0.41
     Gou
    -0.40
     fern
    -0.40
    Personendaten
    -0.40
    culadora
    -0.40
     tourmaline
    -0.40
    POSITIVE LOGITS
     usually
    1.63
    Usually
    1.59
     Usually
    1.55
    usually
    1.47
    Usual
    1.34
     typically
    1.31
     normally
    1.31
     zwykle
    1.27
    Typically
    1.27
    normally
    1.26
    Act Density 0.260%

    No Known Activations