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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Before" indicating prior events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cest
    -0.15
    ëħĢ
    -0.14
    achine
    -0.14
    igm
    -0.13
    ä¸Ģä¸ĭ
    -0.13
    имо
    -0.13
    maint
    -0.13
    cel
    -0.13
    urv
    -0.13
    perial
    -0.12
    POSITIVE LOGITS
    hand
    0.40
     they
    0.40
     anyone
    0.38
     anybody
    0.35
     anything
    0.35
     any
    0.35
     we
    0.34
    -hand
    0.33
     you
    0.31
    HAND
    0.31
    Act Density 0.083%

    No Known Activations