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

    Neuronpedia

    INDEX
    Explanations

    pronouns and linking verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    href
    -0.61
     OWN
    -0.61
    enburg
    -0.60
    nown
    -0.60
     thriving
    -0.59
     infringing
    -0.59
    tering
    -0.59
     payday
    -0.58
     skim
    -0.58
     exploits
    -0.58
    POSITIVE LOGITS
    ologists
    0.82
    icians
    0.79
    ums
    0.76
    abases
    0.76
    essors
    0.76
    ologist
    0.76
    INAL
    0.74
    ference
    0.72
    atively
    0.71
    ennial
    0.69
    Act Density 0.020%

    No Known Activations