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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the passage of time or events occurring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldi
    -0.15
    ATUS
    -0.15
    ue
    -0.14
    iets
    -0.14
    alis
    -0.14
    uela
    -0.13
     tuto
    -0.13
    atus
    -0.13
     conco
    -0.13
    ensen
    -0.13
    POSITIVE LOGITS
     follows
    0.33
     follow
    0.27
    follow
    0.23
     FOLLOW
    0.21
     Follow
    0.21
    Follow
    0.20
     days
    0.19
     following
    0.19
    _follow
    0.19
     heels
    0.19
    Act Density 0.021%

    No Known Activations