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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conjunctions and transitions within sentences

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitions within complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igr
    -0.68
    rollers
    -0.67
    ocating
    -0.67
    hemer
    -0.67
    skin
    -0.66
    ember
    -0.65
    pering
    -0.64
    iard
    -0.63
    icking
    -0.62
    olving
    -0.62
    POSITIVE LOGITS
    withstanding
    0.90
     doubtless
    0.90
     rightly
    0.87
     fortunately
    0.85
     confir
    0.81
     repeated
    0.79
    soType
    0.76
    perhaps
    0.75
     perhaps
    0.74
     paraph
    0.74
    Act Density 0.244%

    No Known Activations