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

    Neuronpedia

    INDEX
    Explanations

    references to social gatherings and alumni events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¢°
    -0.14
    argas
    -0.14
    otec
    -0.13
    strup
    -0.13
    UNDLE
    -0.13
    igi
    -0.13
    _learning
    -0.12
    preh
    -0.12
    training
    -0.12
    /Instruction
    -0.12
    POSITIVE LOGITS
     alumni
    0.49
     Alumni
    0.48
     reunion
    0.45
     alum
    0.44
     al
    0.40
     reun
    0.39
    /al
    0.35
    umni
    0.33
     reunited
    0.31
    -al
    0.31
    Act Density 0.062%

    No Known Activations