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

    Neuronpedia

    INDEX
    Explanations

    references to power and force dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.44
     AssemblyCulture
    -0.43
    RTCK
    -0.42
    theless
    -0.42
    ymce
    -0.41
    rousel
    -0.41
    Rhestr
    -0.41
    覧
    -0.39
    sidemargin
    -0.39
    InitVars
    -0.38
    POSITIVE LOGITS
     force
    4.31
    force
    3.86
     Force
    3.80
    Force
    3.64
     FORCE
    3.56
    FORCE
    3.13
     forces
    2.91
    forces
    2.72
     Forces
    2.69
     fuerza
    2.61
    Act Density 0.134%

    No Known Activations