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

    Neuronpedia

    INDEX
    Explanations

    adverbs or adverbial phrases that strengthen the tone of a statement

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing strong opinions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Journals
    -0.75
     Chaser
    -0.73
    adr
    -0.73
     Therapy
    -0.72
    arters
    -0.69
    OTOS
    -0.69
     Procedure
    -0.69
     Victims
    -0.69
     Gorge
    -0.68
     Sanct
    -0.68
    POSITIVE LOGITS
     enough
    1.01
     strongly
    0.91
     correlated
    0.87
     differentiated
    0.81
     appreciated
    0.76
     typed
    0.74
     disagree
    0.73
     insulated
    0.73
    enough
    0.72
     initialized
    0.72
    Act Density 0.005%

    No Known Activations