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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ed
    -0.17
    in
    -0.17
    roll
    -0.16
    apos
    -0.15
    ýt
    -0.15
     behalf
    -0.15
    ix
    -0.14
    nder
    -0.14
    ndef
    -0.14
    ctor
    -0.14
    POSITIVE LOGITS
    UAGE
    0.17
    oret
    0.15
    rax
    0.15
    otime
    0.15
    ãĥ£
    0.14
    RetVal
    0.14
    	TokenName
    0.14
    cion
    0.14
    ething
    0.14
    éĺª
    0.14
    Act Density 0.171%

    No Known Activations