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

    Neuronpedia

    INDEX
    Explanations

    terms related to restrictions and conditions for communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -0.64
    meric
    -0.52
     Projek
    -0.51
    tiche
    -0.50
    гал
    -0.50
     Ani
    -0.48
    anze
    -0.48
     Kamal
    -0.48
     Surv
    -0.48
    Ani
    -0.48
    POSITIVE LOGITS
    ArrowToggle
    0.75
    IsMutable
    0.72
     timing
    0.69
    Timing
    0.66
    +#+#
    0.65
     opportune
    0.63
    タイミング
    0.60
     Timing
    0.59
     незавершена
    0.56
    fromnode
    0.56
    Act Density 0.318%

    No Known Activations