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

    Neuronpedia

    INDEX
    Explanations

    phrases related to someone telling a story or providing information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "told" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adesh
    -0.84
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.78
    pmwiki
    -0.76
    é¾įåĸļ士
    -0.75
    claimer
    -0.73
    mite
    -0.72
    aband
    -0.71
    yrights
    -0.71
    âķ
    -0.69
    prime
    -0.69
    POSITIVE LOGITS
     investigators
    1.28
     reporters
    1.22
     detectives
    1.12
     jurors
    1.06
     BuzzFeed
    1.06
     TMZ
    1.02
     authorities
    0.98
     me
    0.97
     HuffPost
    0.97
     interviewer
    0.94
    Act Density 0.074%

    No Known Activations