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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mechanical objects and tools

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IBLE
    -0.69
    «ĺ
    -0.68
     correction
    -0.66
     condol
    -0.65
     hug
    -0.65
    omics
    -0.65
    idth
    -0.64
     tyr
    -0.64
     allowance
    -0.63
     forestry
    -0.63
    POSITIVE LOGITS
     Though
    1.30
     Its
    1.30
     Unlike
    1.28
     According
    1.26
     Known
    1.24
     Although
    1.22
     Each
    1.21
     Additionally
    1.21
     Despite
    1.20
     Along
    1.19
    Act Density 0.322%

    No Known Activations