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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional states or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alle
    -0.14
    emento
    -0.14
    دار
    -0.14
    иÑĢ
    -0.14
    .Std
    -0.14
    expired
    -0.13
    oris
    -0.13
    .struct
    -0.13
    essen
    -0.13
    itals
    -0.13
    POSITIVE LOGITS
     strongly
    0.27
     compelled
    0.26
     comfortable
    0.23
     duty
    0.22
     like
    0.21
     Duty
    0.19
     confident
    0.19
     obliged
    0.19
     inclined
    0.18
    comfort
    0.18
    Act Density 0.029%

    No Known Activations