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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional responses related to movies and storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.76
    }],
    -0.67
     houſe
    -0.66
     Monfieur
    -0.65
     itſelf
    -0.65
     themſelves
    -0.64
    arquía
    -0.61
     Teufel
    -0.61
     ;
    -0.60
     Busy
    -0.59
    POSITIVE LOGITS
     sentimental
    1.05
     emotional
    0.97
     heartfelt
    0.93
     heartwarming
    0.89
     emotionally
    0.83
     poignant
    0.81
     sentiment
    0.80
    emotional
    0.79
     tenderly
    0.78
     emotion
    0.77
    Act Density 0.450%

    No Known Activations