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

    Neuronpedia

    INDEX
    Explanations

    generic placeholders or indicators of conversational pauses and transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    γνω
    -0.59
    AppMethodBeat
    -0.52
     légende
    -0.51
    每一次
    -0.49
     fiecare
    -0.49
    Each
    -0.49
     aparente
    -0.48
    SequentialGroup
    -0.48
     vuol
    -0.47
    の原因
    -0.47
    POSITIVE LOGITS
     something
    1.51
     preferably
    1.37
    something
    1.37
     Something
    1.28
    Something
    1.27
     Preferably
    1.27
     anything
    1.26
    preferably
    1.25
    anything
    1.15
     Anything
    1.15
    Act Density 0.341%

    No Known Activations