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

    Neuronpedia

    INDEX
    Explanations

    phrases related to casual conversation and social interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Additionally
    -0.81
    Furthermore
    -0.81
     Additionally
    -0.75
     Furthermore
    -0.74
     poiché
    -0.67
    Moreover
    -0.67
     additionally
    -0.63
    bigsqcup
    -0.61
     furthermore
    -0.61
     Moreover
    -0.60
    POSITIVE LOGITS
     gotta
    1.10
     need
    1.06
     gonna
    1.05
     Gonna
    1.02
     dunno
    1.00
     got
    0.99
    gonna
    0.97
    Gonna
    0.96
     Need
    0.95
     Gotta
    0.94
    Act Density 0.337%

    No Known Activations