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

    Neuronpedia

    INDEX
    Explanations

    arrows used in programming or data syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     JIM
    -0.69
     conversation
    -0.66
    JIM
    -0.66
     Heim
    -0.66
    腳
    -0.63
    юрпри
    -0.62
     pab
    -0.62
     WIND
    -0.61
     Esch
    -0.60
     Plow
    -0.59
    POSITIVE LOGITS
     =>
    1.88
    =>
    1.66
    )=>
    1.45
    "=>
    1.31
     =>
    1.23
    =>"
    1.18
    (()=>
    1.16
    '=>
    1.12
     ()=>
    1.11
     ⇒
    1.11
    Act Density 0.029%

    No Known Activations