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

    Neuronpedia

    INDEX
    Explanations

    strongly negative or unpleasant adjectives

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to negative emotions and suffering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icipated
    -0.94
    encers
    -0.87
    encer
    -0.78
    reek
    -0.76
    RAFT
    -0.76
    prints
    -0.74
    lean
    -0.74
    itives
    -0.74
    MpServer
    -0.73
    ioch
    -0.73
    POSITIVE LOGITS
     miserable
    0.98
     wretched
    0.81
     misery
    0.79
     dismal
    0.78
     lonely
    0.78
     nightmare
    0.78
     pathetic
    0.75
     motel
    0.71
     depressing
    0.69
     miser
    0.69
    Act Density 0.022%

    No Known Activations