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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotions and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gio
    -0.15
    aru
    -0.15
    ddl
    -0.15
    arda
    -0.15
    nostic
    -0.15
    AtPath
    -0.14
    ite
    -0.14
     str
    -0.14
     Dram
    -0.14
    nosis
    -0.14
    POSITIVE LOGITS
     feelings
    0.28
     offended
    0.27
     offence
    0.21
     offend
    0.21
     hurt
    0.20
     sensitive
    0.20
     sensit
    0.20
     offense
    0.20
     Hurt
    0.20
     sensitivity
    0.19
    Act Density 0.047%

    No Known Activations