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

    Neuronpedia

    INDEX
    Explanations

    variable assignments and references, particularly those related to dollar sign-prefixed variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.03
     Efq
    -1.00
     ſever
    -0.98
     Cæsar
    -0.96
     faſt
    -0.95
     fevere
    -0.94
     myſelf
    -0.93
     themſelves
    -0.93
     doubtnut
    -0.92
     raiſ
    -0.90
    POSITIVE LOGITS
    ="<?=$
    0.91
    <?=$
    0.85
    udit
    0.73
     $
    0.72
    ="{{$
    0.71
    '][$
    0.66
    "=>$
    0.65
     this
    0.64
    enumi
    0.63
    '],$
    0.63
    Act Density 0.061%

    No Known Activations