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

    Neuronpedia

    INDEX
    Explanations

    expressions related to positive experiences and highlights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Mess
    -0.14
    ajs
    -0.14
     Dup
    -0.14
    onth
    -0.14
    oft
    -0.14
    echan
    -0.14
    å°ij女
    -0.13
     Mess
    -0.13
    RL
    -0.13
     mess
    -0.13
    POSITIVE LOGITS
     about
    0.41
    About
    0.35
     About
    0.35
    about
    0.34
     ABOUT
    0.32
    _about
    0.31
     aspect
    0.30
    .about
    0.28
     tentang
    0.28
    aspect
    0.27
    Act Density 0.063%

    No Known Activations