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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal technicalities and constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hai
    -0.82
    ahime
    -0.78
    eg
    -0.74
    soDeliveryDate
    -0.72
    itton
    -0.71
    ortment
    -0.69
    ometimes
    -0.67
    essler
    -0.65
    enhagen
    -0.64
    ku
    -0.60
    POSITIVE LOGITS
     whatsoever
    1.74
     nor
    1.24
     anymore
    0.95
     slightest
    0.93
    nor
    0.91
     anywhere
    0.91
     except
    0.87
     EVER
    0.82
    except
    0.80
     anybody
    0.79
    Act Density 0.384%

    No Known Activations