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

    Neuronpedia

    INDEX
    Explanations

    phrases related to collisions or crashes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "into."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    redo
    -0.79
    hop
    -0.72
    lege
    -0.68
    awaru
    -0.67
    TERN
    -0.67
    nah
    -0.66
    ior
    -0.66
    oris
    -0.66
    dl
    -0.66
    construct
    -0.65
    POSITIVE LOGITS
     Valhalla
    0.82
     infinity
    0.75
     fists
    0.73
     thirds
    0.69
     volcan
    0.67
     Eternity
    0.66
     thin
    0.65
     Ital
    0.64
    asted
    0.63
     Destiny
    0.63
    Act Density 0.055%

    No Known Activations