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

    Neuronpedia

    INDEX
    Explanations

    expressions of continuity and preservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ph
    -0.61
    ньше
    -0.60
     Bry
    -0.60
     graines
    -0.58
     TO
    -0.58
    omitempty
    -0.58
    engesch
    -0.57
     Ph
    -0.57
    glam
    -0.57
    gesch
    -0.57
    POSITIVE LOGITS
     maintain
    1.98
     maintained
    1.97
     Maintain
    1.94
     maintenance
    1.93
     maintaining
    1.90
    Maintain
    1.87
     Maintaining
    1.85
    Maintaining
    1.82
     maintains
    1.82
    maintain
    1.82
    Act Density 0.057%

    No Known Activations