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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a list or sequence of items

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "as follows" and variations indicating lists or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sweat
    -0.55
    ?),
    -0.52
    Ħ¢
    -0.51
     damned
    -0.51
     slammed
    -0.51
    ?).
    -0.51
    iami
    -0.50
     rebound
    -0.50
     shortages
    -0.50
    ©¶æ¥µ
    -0.50
    POSITIVE LOGITS
    :[
    1.49
    :(
    1.23
    :-
    1.23
    :
    1.21
    *:
    1.20
    :"
    1.15
    .:
    1.04
    :{
    1.03
    :,
    0.99
    :'
    0.94
    Act Density 0.137%

    No Known Activations