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

    Neuronpedia

    INDEX
    Explanations

    words related to structural components and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ihan
    -0.16
    asher
    -0.15
     recent
    -0.15
    jerne
    -0.14
     famously
    -0.14
    oids
    -0.14
    udios
    -0.14
    resher
    -0.14
    inherits
    -0.14
     buffered
    -0.14
    POSITIVE LOGITS
    both
    0.27
     both
    0.26
     BOTH
    0.21
    Both
    0.21
     Both
    0.20
     throughout
    0.19
     combinations
    0.19
    combination
    0.18
    initial
    0.18
     både
    0.18
    Act Density 0.033%

    No Known Activations